© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14003
    Prev
    Next
    INDEX
    Explanations

    0800/111 and helping numbers

    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
    익
    1.74
    EY
    1.72
    𝕕
    1.70
    Sel
    1.65
    γη
    1.64
    Chk
    1.58
     blemishes
    1.58
    SV
    1.58
    ڈن
    1.58
    𝙳
    1.58
    POSITIVE LOGITS
    ي
    2.19
    etição
    1.78
    rú
    1.63
    ométrique
    1.62
    rafo
    1.60
    ের
    1.57
    raction
    1.53
    et
    1.52
    etem
    1.51
    rocess
    1.50
    Activations Density 0.000%

    No Known Activations