© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117210
    Prev
    Next
    INDEX
    Explanations

    concept

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

    The neuron fires on individual “e” character tokens.

    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
     first
    -0.92
    ･･
    -0.86
    ：　
    -0.86
    ския
    -0.86
     wholly
    -0.84
     Keeping
    -0.83
    riwal
    -0.81
    ançon
    -0.79
     just
    -0.79
     purely
    -0.79
    POSITIVE LOGITS
    CHAT
    0.90
    prüfung
    0.87
     bút
    0.86
     ove
    0.85
     beige
    0.85
     rectangular
    0.83
    orche
    0.82
     unn
    0.81
    holung
    0.81
     travaux
    0.80
    Activations Density 0.000%

    No Known Activations