© 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. 65008
    Prev
    Next
    INDEX
    Explanations

    effective.rock.image.joy.online reality.days.use.want

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

    abstract concepts and fields

    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
    ামিন
    0.47
    cas
    0.45
    variant
    0.44
    =>$
    0.44
    santa
    0.44
    in
    0.43
    cut
    0.43
    expert
    0.43
    regional
    0.43
     And
    0.43
    POSITIVE LOGITS
    ائ
    0.49
    گ
    0.49
     correção
    0.48
    ای
    0.47
    -
    0.47
    <0x07>
    0.46
    ﻧ
    0.46
     言
    0.45
    الوجی
    0.45
     الر
    0.45
    Activations Density 0.000%

    No Known Activations