© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80736
    Prev
    Next
    INDEX
    Explanations

    medical & software terms

    np_acts-logits-general · gemini-2.5-flash-lite

    newline characters or paragraph breaks in text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects commercial or promotional website references and booking‐call-to-action language (e.g. “.com,” “secure,” “book,” “travellers”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     which
    -0.80
     internazionali
    -0.74
    这本书
    -0.74
     Rotary
    -0.74
     several
    -0.74
    achuca
    -0.73
     plenty
    -0.73
    交叉
    -0.72
    raš
    -0.72
     includes
    -0.71
    POSITIVE LOGITS
    viu
    0.84
    lleri
    0.81
    gotta
    0.79
    Sqft
    0.78
     alimentaires
    0.78
     précédents
    0.77
    openssl
    0.77
     coffre
    0.77
    sofa
    0.77
    Sze
    0.77
    Activations Density 0.001%

    No Known Activations