© 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. 251887
    Prev
    Next
    INDEX
    Explanations

    our sympathy and tribute stores

    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
    EndDate
    0.42
    యో
    0.41
     badly
    0.40
     Nazi
    0.40
    0.39
     nasty
    0.39
     siku
    0.39
    _
    0.39
     LocalDate
    0.39
    怼
    0.38
    POSITIVE LOGITS
     एक्टिव
    0.53
     activated
    0.50
     섬
    0.49
     मधुमेह
    0.49
    activated
    0.47
     नेक
    0.47
     શુભેચ્છ
    0.46
    aronne
    0.45
    ᱖
    0.45
    quila
    0.45
    Activations Density 0.004%

    No Known Activations