© 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. 98402
    Prev
    Next
    INDEX
    Explanations

    investigation, price, trends, books

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

    laws, states, concepts

    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
    ーストラリア
    0.50
     ανε
    0.50
    raft
    0.47
    osof
    0.46
    荿
    0.45
    濂
    0.44
    .";
    0.44
     ப
    0.43
    reibung
    0.43
    }.",
    0.43
    POSITIVE LOGITS
     convo
    0.48
     scrutinized
    0.46
     initializes
    0.46
     resolver
    0.45
     terminated
    0.42
     terminate
    0.42
     prote
    0.42
     centralized
    0.42
     donating
    0.42
    HOOK
    0.41
    Activations Density 0.001%

    No Known Activations