© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199247
    Prev
    Next
    INDEX
    Explanations

    grease-fighting power

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

    directly align or support

    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
    Negative Logits
    ERIAL
    0.56
     atth
    0.55
     टारगेट
    0.53
     necesito
    0.47
     poseen
    0.47
     pizarra
    0.46
    пто
    0.46
    DAILY
    0.46
    ﻜ
    0.45
    Headline
    0.45
    POSITIVE LOGITS
    osit
    0.47
     Heisenberg
    0.47
    azione
    0.44
    la
    0.43
    aan
    0.43
    omorf
    0.42
    isc
    0.42
     परिवेश
    0.42
     Wahr
    0.41
     zippered
    0.41
    Activations Density 0.000%

    No Known Activations