© 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. 28736
    Prev
    Next
    INDEX
    Explanations

    country music

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

    AI developers and models

    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
    곶
    0.55
     propios
    0.53
     první
    0.52
     pierwsze
    0.48
    eneuve
    0.46
     таких
    0.46
    وجود
    0.45
     ресурсов
    0.45
     impot
    0.44
     Ressourcen
    0.44
    POSITIVE LOGITS
    fieldName
    0.49
    End
    0.48
    Empire
    0.46
    ENDMENT
    0.46
     Empire
    0.46
     ダ
    0.45
    LA
    0.44
    Division
    0.44
    AKI
    0.44
     Petitioner
    0.44
    Activations Density 0.000%

    No Known Activations