© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 218308
    Prev
    Next
    INDEX
    Explanations

    specific words followed by other words

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

    crack cocaine

    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
    dfs
    0.44
    εται
    0.43
     karo
    0.43
    两种
    0.42
    린
    0.42
    рын
    0.42
    sl
    0.41
    ные
    0.41
     renaissance
    0.41
    炭
    0.41
    POSITIVE LOGITS
     Socialista
    0.52
     Hell
    0.47
     Illegal
    0.47
     marido
    0.47
    ("%
    0.46
     だ
    0.46
     دقیقه
    0.46
     El
    0.46
    covers
    0.46
     Acerca
    0.46
    Activations Density 0.000%

    No Known Activations