© 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. 182036
    Prev
    Next
    INDEX
    Explanations

    herd, craving, jump, allocated

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

    GitHub Copilot IDE context

    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
    а
    0.47
    modelLogin
    0.47
     Rosario
    0.46
     tipo
    0.45
    aminated
    0.45
    itemName
    0.43
     गर्नु
    0.43
     timeLeft
    0.42
     그러면은
    0.42
     combination
    0.42
    POSITIVE LOGITS
     ખે
    0.49
    mathbf
    0.47
     Dynamical
    0.44
    t
    0.44
     Beacon
    0.42
    Tracing
    0.42
     regardless
    0.41
    BatchNorm
    0.41
    instagood
    0.41
     Regardless
    0.41
    Activations Density 0.001%

    No Known Activations