© 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. 243133
    Prev
    Next
    INDEX
    Explanations

    figure and then a noun

    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
    厕
    0.54
     carport
    0.51
     domicilio
    0.51
    扑
    0.49
    闱
    0.49
    边
    0.46
    外国
    0.46
    િયો
    0.46
    厅
    0.46
     fecha
    0.46
    POSITIVE LOGITS
     fists
    0.50
    dem
    0.46
    ady
    0.46
    rys
    0.46
    ble
    0.44
    andom
    0.44
     syringes
    0.44
     Visions
    0.43
     rockets
    0.43
     работой
    0.43
    Activations Density 0.001%

    No Known Activations