© 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. 157923
    Prev
    Next
    INDEX
    Explanations

    network structure

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

    violence and sex work

    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
    ሃኒ
    0.52
    ूरत
    0.48
    டும்ப
    0.48
     ني
    0.48
     HOURS
    0.48
    ટ
    0.48
    怎么样
    0.46
    ào
    0.46
     коми
    0.46
    ండ్
    0.46
    POSITIVE LOGITS
     mangrove
    0.40
     multivalued
    0.39
    n
    0.38
     nonequilibrium
    0.38
     unenforceable
    0.38
     -
    0.38
     Sobolev
    0.37
     Dirichlet
    0.37
     deterrence
    0.37
     elliptic
    0.36
    Activations Density 0.000%

    No Known Activations