© 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. 134006
    Prev
    Next
    INDEX
    Explanations

    honor Rosemary

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

    bypass restrictions or preferences

    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
    SS
    0.48
    timestamps
    0.46
    GD
    0.43
    Capability
    0.42
    都合
    0.41
    CTest
    0.41
    isa
    0.41
    {#
    0.41
    readyState
    0.41
    bodyA
    0.41
    POSITIVE LOGITS
    мум
    0.50
    थ
    0.48
     مرگ
    0.48
     YELLOW
    0.47
     Polres
    0.47
     successivo
    0.47
    ौं
    0.46
     ambil
    0.46
    ມື
    0.46
     मुख
    0.46
    Activations Density 0.000%

    No Known Activations