© 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. 10889
    Prev
    Next
    INDEX
    Explanations

    comforting blanket

    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
    طات
    1.75
    iu
    1.67
    ας
    1.61
    掴
    1.57
    makeConstraints
    1.56
    iem
    1.56
    çuk
    1.51
    imos
    1.50
    ுகளில்
    1.49
    阡
    1.49
    POSITIVE LOGITS
     Sumber
    1.90
     Arn
    1.88
    Sumber
    1.85
     Source
    1.72
    Fuente
    1.68
    source
    1.68
     Berry
    1.67
    Га
    1.67
     Break
    1.64
    Break
    1.63
    Activations Density 0.003%

    No Known Activations