© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 959
    Prev
    Next
    INDEX
    Explanations

    LaTeX figure placement specifier `[h!]`

    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_13_width_65k_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
     on
    1.12
     at
    1.12
    -
    1.06
     (
    1.05
    ,
    1.04
     in
    1.01
     for
    0.97
     to
    0.94
     with
    0.90
     and
    0.88
    POSITIVE LOGITS
    𒁹
    1.96
    𒅕
    1.94
    𒅅
    1.94
    𒌐
    1.94
    𒋛
    1.94
     ہُما
    1.93
    𒍣
    1.92
    𒈹
    1.92
    𒁁
    1.91
    𒉪
    1.91
    Activations Density 0.080%

    No Known Activations