© 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. 88006
    Prev
    Next
    INDEX
    Explanations

    Nebraska, Greensboro, North Carolina

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

    checking for substrings

    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
    在
    0.49
    Autoresizing
    0.48
     INIS
    0.48
     పథ
    0.48
     vlo
    0.46
     sche
    0.46
     ASSOCI
    0.46
    畩
    0.45
    鬚
    0.45
     variational
    0.44
    POSITIVE LOGITS
     renovación
    0.52
    cooler
    0.49
    вання
    0.47
    Disabled
    0.47
    🔧
    0.46
    gripper
    0.46
    Gregor
    0.46
    explosion
    0.45
    サート
    0.44
     basada
    0.43
    Activations Density 0.004%

    No Known Activations