© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3173
    Prev
    Next
    INDEX
    Explanations

    setting realistic goals and questions

    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
    -
    1.17
    fing
    1.17
    fut
    1.11
    ag
    1.09
    ly
    1.05
    ram
    1.04
     night
    0.97
    ocarpus
    0.94
    rogen
    0.94
     hour
    0.93
    POSITIVE LOGITS
    КИ
    1.39
    اتھن
    1.37
    최
    1.37
    Databaze
    1.35
    <unused1355>
    1.35
     strListName
    1.34
     avaliação
    1.33
     vyber
    1.33
    ZIONE
    1.33
     GCBO
    1.33
    Activations Density 0.201%

    No Known Activations