© 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. 162128
    Prev
    Next
    INDEX
    Explanations

    TOUR DURATION:

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

    earlier band; useful for; to assimilate

    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
    ﺟ
    0.47
    Parliament
    0.46
    轶
    0.46
    消費
    0.44
     Rajya
    0.44
    احنا
    0.44
    كلمنا
    0.43
    副
    0.42
     electroly
    0.42
    唾
    0.42
    POSITIVE LOGITS
    aran
    0.49
    ladı
    0.49
    cled
    0.48
     சென்ன
    0.48
    lades
    0.47
     Уен
    0.47
     М
    0.46
     Gonçalves
    0.46
    aper
    0.46
     ус
    0.46
    Activations Density 0.001%

    No Known Activations