© 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. 237958
    Prev
    Next
    INDEX
    Explanations

    as well; using the; paid for

    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
    ხვ
    0.52
    别
    0.50
    ிருந்தால்
    0.50
    在一个
    0.49
     然后
    0.49
    点が
    0.49
    论
    0.48
    混乱
    0.48
    颞
    0.48
    然後
    0.47
    POSITIVE LOGITS
     phenotype
    0.49
    Beta
    0.48
    s
    0.47
     Cory
    0.45
     cytoskeleton
    0.44
     best
    0.44
     polymorphic
    0.44
     Len
    0.43
    Time
    0.42
    title
    0.42
    Activations Density 0.000%

    No Known Activations