© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2067
    Prev
    Next
    INDEX
    Explanations

    skills and processes

    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
    <unused119>
    1.60
     ہُما
    1.57
    nBitCount
    1.55
     trataro
    1.55
    ുമിത്ര
    1.51
    gramModel
    1.51
    <unused881>
    1.51
    getRedTeam
    1.50
    addPreferred
    1.49
    nbhost
    1.49
    POSITIVE LOGITS
    1.11
     was
    1.11
    ↵↵
    1.08
     had
    1.08
     K
    0.99
     who
    0.99
     is
    0.99
     not
    0.98
     became
    0.98
     were
    0.97
    Activations Density 0.383%

    No Known Activations