© 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-16K
    7. 11847
    Prev
    Next
    INDEX
    Explanations

    never followed by verbs

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

    negation or prohibition

    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_16k_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
     are
    0.82
     an
    0.73
    ில்
    0.72
    aning
    0.71
     vestiges
    0.71
    ieniu
    0.68
    ਾ
    0.68
    ی
    0.67
     bindings
    0.67
     hinders
    0.67
    POSITIVE LOGITS
    Never
    1.11
    never
    1.09
     NEVER
    1.09
     jamás
    1.09
     Never
    1.05
     nooit
    0.97
     কখনও
    0.96
    Nunca
    0.93
     never
    0.92
     कभी
    0.83
    Activations Density 0.157%

    No Known Activations