© 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. 58177
    Prev
    Next
    INDEX
    Explanations

    exploring, via, championships, possibility

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

    technical terms and structured data

    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
     معاون
    0.52
    Supporting
    0.49
    ဖြစ်သည်။
    0.47
    Permissions
    0.47
    ranks
    0.46
     وصف
    0.46
    Λ
    0.45
    a
    0.44
    Middle
    0.44
     सौरभ
    0.44
    POSITIVE LOGITS
    вить
    0.50
     recordar
    0.48
    жить
    0.47
    zu
    0.46
     usaha
    0.46
     Nge
    0.45
     Fórmula
    0.45
    섰
    0.45
     Neces
    0.45
    строи
    0.44
    Activations Density 0.000%

    No Known Activations