© 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. 120480
    Prev
    Next
    INDEX
    Explanations

    allies and election

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

    allocating/occupying/separating elements

    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
     Il
    0.53
    ana
    0.51
    rtl
    0.50
    /
    0.48
    TI
    0.48
    aves
    0.47
    idget
    0.47
    act
    0.46
    te
    0.46
    lev
    0.46
    POSITIVE LOGITS
    زيد
    0.55
     produção
    0.50
    枥
    0.49
    𝙤
    0.48
    ્ર
    0.47
    стта
    0.47
    碴
    0.47
    Გ
    0.47
    لاک
    0.47
     opérés
    0.47
    Activations Density 0.000%

    No Known Activations