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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64940
    Prev
    Next
    INDEX
    Explanations

    android version or message metadata

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

    The neuron flags programming‐language syntax elements—reserved keywords (like SELECT, FROM, COUNT), punctuation (dots, parentheses), and code identifiers.

    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
    六十
    -0.70
    援助
    -0.68
     Glä
    -0.66
     berusaha
    -0.66
     melindungi
    -0.65
     menetapkan
    -0.64
     memenangkan
    -0.63
    知的
    -0.63
     berkomunikasi
    -0.63
     harus
    -0.63
    POSITIVE LOGITS
    multip
    1.08
    mensaje
    1.05
    Messaging
    1.04
     Magne
    1.02
    metadata
    1.02
    messages
    1.02
     Mortality
    1.02
    MemoryStream
    1.00
    markers
    1.00
    mensagem
    0.99
    Activations Density 0.049%

    No Known Activations