© 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. 71938
    Prev
    Next
    INDEX
    Explanations

    housing, plans, and finances

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

    descriptive options and specifics

    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
    ad
    0.60
    டி
    0.54
    をはじめ
    0.50
    са
    0.50
    να
    0.47
    at
    0.47
    rington
    0.47
    Ι
    0.46
    選
    0.46
    صب
    0.45
    POSITIVE LOGITS
     väč
    0.49
     başladı
    0.47
     seção
    0.47
     algumas
    0.46
     maneira
    0.46
     pier
    0.46
     piers
    0.46
     plais
    0.44
     kame
    0.44
     condições
    0.43
    Activations Density 0.000%

    No Known Activations