© 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. 33784
    Prev
    Next
    INDEX
    Explanations

    date followed by month

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

    Russia, rainbow, Janet, snake, egg

    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
     North
    0.51
     如
    0.45
     H
    0.44
     repeatedly
    0.43
     carbohyd
    0.43
    </h3>
    0.43
     Departments
    0.43
     <!
    0.42
    ib
    0.42
     கே
    0.42
    POSITIVE LOGITS
    هایی
    0.53
    пози
    0.50
     مربع
    0.49
    ﻷ
    0.48
     الاجتماعي
    0.48
     जुटा
    0.47
     ضروری
    0.46
    𝔱
    0.45
    یرو
    0.45
     kristall
    0.45
    Activations Density 0.000%

    No Known Activations