© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 68862
    Prev
    Next
    INDEX
    Explanations

    consequences and advice

    np_acts-logits-general · gemini-2.5-flash-lite

    descriptions of states or emotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    лес
    0.50
    开拓
    0.47
     Ө
    0.46
     проекту
    0.45
    𝗹
    0.45
     copia
    0.45
    صیٰ
    0.45
     effluents
    0.44
     ಹೊರ
    0.44
     тому
    0.43
    POSITIVE LOGITS
    Sincerely
    0.47
    <0x80>
    0.47
    ဲ့
    0.44
     Dieu
    0.43
    r
    0.42
     Confederation
    0.41
    rq
    0.40
     Presbyterian
    0.40
     Socks
    0.39
     Jesus
    0.39
    Activations Density 0.001%

    No Known Activations