© 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
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 309
    Prev
    Next
    INDEX
    Explanations

    national helpline for substance abuse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     
    0.83
    ,
    0.66
     (
    0.65
     the
    0.64
     and
    0.63
    .
    0.63
    ↵
    0.63
      
    0.62
     a
    0.62
    ↵↵
    0.61
    POSITIVE LOGITS
    <unused75>
    0.88
    MathMarks
    0.88
    <unused17>
    0.86
    <unused25>
    0.86
    EnglishMarks
    0.85
    <unused44>
    0.83
    rbrakk
    0.83
    jalpha
    0.83
    <unused23>
    0.83
    <unused72>
    0.82
    Activations Density 0.346%

    No Known Activations