© 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. 188178
    Prev
    Next
    INDEX
    Explanations

    places and logistics

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

    defining relationships or comparisons

    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
    Ｍ
    0.51
     fica
    0.49
    Ｔ
    0.45
     pr
    0.44
     Pratt
    0.44
     prenn
    0.44
    であれば
    0.44
     ay
    0.44
    ﻰ
    0.43
    ID
    0.43
    POSITIVE LOGITS
    èg
    0.47
    ضافة
    0.47
    routing
    0.44
    是一些
    0.43
    selen
    0.42
    alow
    0.41
    acup
    0.41
    opera
    0.41
    恋
    0.41
    ütter
    0.41
    Activations Density 0.000%

    No Known Activations