© 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. 98008
    Prev
    Next
    INDEX
    Explanations

    registration number

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

    specific named entities and concepts

    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
    ﺋ
    0.49
    ISTICS
    0.44
     법칙
    0.44
     കർ
    0.43
    ousands
    0.42
     Acura
    0.41
     Bağ
    0.41
     جوړونکي
    0.41
    ி
    0.40
    ീ
    0.40
    POSITIVE LOGITS
     aliqu
    0.48
     достаточно
    0.46
    rift
    0.46
     αυτό
    0.45
     由
    0.45
    ,}
    0.44
    esehen
    0.43
     довольно
    0.43
    orney
    0.43
    রণ
    0.42
    Activations Density 0.000%

    No Known Activations