© 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. 161839
    Prev
    Next
    INDEX
    Explanations

    specific units of measure

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

    focus on existing

    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
    ﻭ
    0.55
    ю
    0.46
    酎
    0.45
     anys
    0.45
    ido
    0.44
    ك
    0.44
    су
    0.44
    Ю
    0.43
     Συν
    0.43
    جام
    0.43
    POSITIVE LOGITS
     দাস
    0.53
    rift
    0.47
    oes
    0.47
    ;?>
    0.46
     spearheaded
    0.45
    steil
    0.45
     paa
    0.45
    rául
    0.44
    Tras
    0.44
     द्वारा
    0.43
    Activations Density 0.000%

    No Known Activations