© 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. 235153
    Prev
    Next
    INDEX
    Explanations

    teacher referring to people

    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
     పార్టీ
    0.48
    ಧಾನ
    0.47
    ంగు
    0.46
    был
    0.45
    зульта
    0.45
    osulf
    0.44
    еш
    0.44
    ી
    0.44
    セキュリティ
    0.44
     букмекерлер
    0.43
    POSITIVE LOGITS
     thorns
    0.46
     Enf
    0.44
     m
    0.44
     monument
    0.43
     thorn
    0.43
     Children
    0.43
     Mening
    0.43
     getDescription
    0.42
     runner
    0.42
     Num
    0.42
    Activations Density 0.002%

    No Known Activations