© 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. 127506
    Prev
    Next
    INDEX
    Explanations

    package or shipping details

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

    Data types and conditions

    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
     foodie
    0.45
    Chiesa
    0.45
    โห
    0.45
     whipped
    0.44
    💒
    0.44
    prison
    0.44
     Beats
    0.43
    ọt
    0.43
     Broccoli
    0.43
    ➡️
    0.43
    POSITIVE LOGITS
    ев
    0.47
     (=
    0.46
     iniziale
    0.45
    拿
    0.45
     induk
    0.44
     bzw
    0.44
     আলোচন
    0.43
     ماشینونو
    0.43
    商标
    0.42
     aktiviert
    0.42
    Activations Density 0.001%

    No Known Activations