© 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. 83907
    Prev
    Next
    INDEX
    Explanations

    writing content in documents

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

    tenant information

    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
     kaleidoscopic
    0.58
    过多
    0.55
     đem
    0.54
     संवै
    0.52
     Tuberculosis
    0.52
     diethyl
    0.50
     traumatic
    0.50
    薈
    0.50
     cytok
    0.49
     tuberculous
    0.49
    POSITIVE LOGITS
    0
    0.46
    shop
    0.46
    markets
    0.40
     ie
    0.39
    tenant
    0.38
    amos
    0.38
    mods
    0.38
    с
    0.38
    village
    0.37
     Maybe
    0.37
    Activations Density 0.001%

    No Known Activations