© 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. 77329
    Prev
    Next
    INDEX
    Explanations

    committed to providing services

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

    first report segments

    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
     Documentation
    0.54
     Client
    0.51
    akes
    0.50
     ព
    0.50
     Proctor
    0.49
    ospital
    0.48
    aroos
    0.48
    apes
    0.47
    !’
    0.47
     Defense
    0.46
    POSITIVE LOGITS
    いて
    0.57
    요
    0.55
    ظر
    0.55
    打ち
    0.53
    פור
    0.52
    유
    0.52
    ي
    0.52
    んで
    0.51
    ции
    0.50
    EVERY
    0.50
    Activations Density 0.002%

    No Known Activations