© 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. 53377
    Prev
    Next
    INDEX
    Explanations

    lower production, scale landscaping, writing/speaking

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

    technical specifications and 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
    ا
    0.48
     Cylinder
    0.46
     Miscellaneous
    0.44
     indig
    0.44
    贝
    0.43
     Clip
    0.43
    佺
    0.43
    مت
    0.42
    Blitz
    0.42
     Bells
    0.41
    POSITIVE LOGITS
     निकलता
    0.50
    謃
    0.50
     लेखन
    0.49
    ೆಂದು
    0.49
     fonctionnent
    0.48
     этапе
    0.48
     لکھ
    0.46
    atthakath
    0.46
    素敵
    0.46
     ਰਾ
    0.46
    Activations Density 0.000%

    No Known Activations