© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 23447
    Prev
    Next
    INDEX
    Explanations

    special content words

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

    negate binary structures or sex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    to
    0.54
    то
    0.48
    posting
    0.46
    م
    0.46
    лін
    0.46
    post
    0.45
    pandemic
    0.44
    ر
    0.43
    switching
    0.43
    б
    0.43
    POSITIVE LOGITS
     correspond
    0.49
     fenómeno
    0.48
     gole
    0.48
     注意
    0.47
     Heated
    0.46
    ప్రత్య
    0.46
     除了
    0.46
     applique
    0.45
     因為
    0.45
     ആണ്
    0.45
    Activations Density 0.000%

    No Known Activations