© 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. 30976
    Prev
    Next
    INDEX
    Explanations

    academic and senior contexts

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

    explaining concepts with examples

    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
    িন
    0.54
    婜
    0.53
     رسید
    0.52
     உயர்ந்த
    0.51
     عرضه
    0.51
    子の
    0.50
     এইরূপে
    0.50
     مسیر
    0.49
    ול
    0.49
     যেরূপ
    0.48
    POSITIVE LOGITS
     Ζ
    0.46
    machen
    0.44
     écrire
    0.44
    zum
    0.44
     acabar
    0.43
    weixin
    0.43
    Z
    0.42
    vaa
    0.42
     THAT
    0.42
    Tiles
    0.42
    Activations Density 0.000%

    No Known Activations