© 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. 163988
    Prev
    Next
    INDEX
    Explanations

    one, 5, Equalities, suppliers

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

    flexibility, affinity

    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
    ！！
    0.51
    ความคิด
    0.49
    доро
    0.47
    焓
    0.44
     Екатерина
    0.44
     Diego
    0.43
    жени
    0.43
    !!");
    0.43
    쁜
    0.43
     Germ
    0.43
    POSITIVE LOGITS
     erstmals
    0.52
    ysteem
    0.50
     نزدیک
    0.49
    harmon
    0.48
     چھ
    0.47
     সামনে
    0.47
    ol
    0.47
    oč
    0.47
    TextureAsset
    0.46
    okar
    0.46
    Activations Density 0.001%

    No Known Activations