© 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-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 10918
    Prev
    Next
    INDEX
    Explanations

    code comments with instructions

    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
    berly
    2.75
    র
    2.42
    et
    2.28
    ла
    2.16
    ore
    2.08
    stein
    2.05
    ed
    2.04
    en
    2.01
    al
    1.99
    ̆
    1.97
    POSITIVE LOGITS
     kaçtır
    2.64
    oldsymbol
    2.58
    靼
    2.58
    此同时
    2.58
     összef
    2.55
    LECTION
    2.55
    miot
    2.53
     paramInt
    2.51
    ್ರೀ
    2.49
    页面存档备份
    2.48
    Activations Density 0.000%

    No Known Activations