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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13974
    Prev
    Next
    INDEX
    Explanations

    listing specific situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    差し
    1.64
    잡
    1.64
    습
    1.51
    できた
    1.50
     कच्छ
    1.48
    ګه
    1.47
    ство
    1.44
    급
    1.43
    ɗ
    1.41
    త్మ
    1.41
    POSITIVE LOGITS
     lending
    1.73
     belongings
    1.56
     Chairs
    1.53
    ອກ
    1.52
     BAN
    1.51
     folding
    1.51
     WPARAM
    1.51
     chairs
    1.50
     peaches
    1.47
     therein
    1.46
    Activations Density 0.000%

    No Known Activations