© 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. 50541
    Prev
    Next
    INDEX
    Explanations

    follow andKingdom workmodel prototypingskill incorrectlyhath rejected

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

    list items and configurations

    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
     wrecked
    0.59
     wreck
    0.50
    败
    0.48
     comest
    0.47
    )，
    0.45
     crumb
    0.45
     edible
    0.45
    还没有
    0.45
     warranted
    0.44
     charred
    0.44
    POSITIVE LOGITS
    motorbike
    0.57
    iß
    0.55
    zeppelin
    0.52
    enemy
    0.52
    <0x0B>
    0.52
    extensions
    0.52
     Sơn
    0.51
    savings
    0.51
     লীগের
    0.49
    saving
    0.49
    Activations Density 0.000%

    No Known Activations