© 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. 61467
    Prev
    Next
    INDEX
    Explanations

    assessments, God, promised, this, bat, IR

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

    divides the court

    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
     perkara
    0.54
     ανά
    0.45
    Twelve
    0.44
    ))],
    0.44
    ধির
    0.43
     simples
    0.43
    ьте
    0.43
    ल्लाला
    0.43
    Eleven
    0.43
    Flora
    0.43
    POSITIVE LOGITS
    쏙
    0.50
     {/*
    0.50
    鋳
    0.47
     таки
    0.46
     Presidents
    0.46
    נ
    0.45
     الصفحة
    0.44
    weight
    0.44
    menopausal
    0.44
    wiches
    0.44
    Activations Density 0.000%

    No Known Activations