© 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. 135226
    Prev
    Next
    INDEX
    Explanations

    Beyoncé pompeii, backup services

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

    electricity was not discovered

    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
     rendah
    0.49
    ᓘ
    0.46
    Ukraine
    0.46
     mustang
    0.43
     elkaar
    0.43
    ｷ
    0.43
     low
    0.42
    Cuenta
    0.42
     delegations
    0.42
     bronze
    0.41
    POSITIVE LOGITS
    prime
    0.49
     Presumably
    0.46
    iphy
    0.45
     Comes
    0.45
    ном
    0.45
    o
    0.45
     Come
    0.45
     केमिस्ट्री
    0.44
     Compounds
    0.43
    いで
    0.42
    Activations Density 0.000%

    No Known Activations