© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11168
    Prev
    Next
    INDEX
    Explanations

    asking for or providing examples

    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_13_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
    ્વાસ
    1.82
    மீ
    1.82
    <0x9F>
    1.76
    ர்
    1.71
     ज़र
    1.70
    fwrite
    1.69
    !\!\
    1.67
    팅
    1.67
    ⎤
    1.67
    顎
    1.67
    POSITIVE LOGITS
    InstrumentedTest
    3.29
     exempl
    1.98
     Cases
    1.97
     pronoun
    1.94
    empi
    1.93
     Exempl
    1.89
     bxa
    1.89
    gery
    1.89
    gry
    1.85
    ogeneous
    1.85
    Activations Density 0.133%

    No Known Activations