© 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. 11761
    Prev
    Next
    INDEX
    Explanations

    making suggestions

    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
    𝒕
    2.97
    𝒚
    2.92
    𝕕
    2.90
    𝒅
    2.88
    ことができる
    2.84
    𝒄
    2.84
    𝒹
    2.79
    PlistBuddy
    2.75
    pgsql
    2.74
    ことができます
    2.74
    POSITIVE LOGITS
    س
    3.26
    ي
    3.12
    꿉
    2.63
    多么
    2.56
    ح
    2.54
    __(/*!
    2.52
    блю
    2.44
    дцать
    2.42
    iselle
    2.42
    ity
    2.37
    Activations Density 0.093%

    No Known Activations