© 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. 98412
    Prev
    Next
    INDEX
    Explanations

    Wall Lights

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

    watch live, meal were, limited by, mg once

    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
    𝑉
    0.49
    Ꮯ
    0.47
    ज्ञान
    0.46
    as
    0.44
    ForSettings
    0.44
    푚
    0.44
    श्री
    0.43
    ቮ
    0.43
     organisme
    0.43
    एमसी
    0.42
    POSITIVE LOGITS
     Böl
    0.47
     Han
    0.45
     Kur
    0.45
     North
    0.45
     वर्णन
    0.45
     Seite
    0.45
     H
    0.44
     Init
    0.44
     Write
    0.44
     W
    0.43
    Activations Density 0.000%

    No Known Activations