© 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. 183894
    Prev
    Next
    INDEX
    Explanations

    installingnew stakeenraged Laksh

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

    corporatism and revolution

    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
     fă
    0.55
     ස්ථා
    0.54
     Tatha
    0.53
     posicion
    0.53
     escalas
    0.52
    舱
    0.52
     escala
    0.52
     आकर्षण
    0.52
    ið
    0.51
     skala
    0.51
    POSITIVE LOGITS
     =$
    0.44
    Lead
    0.43
    Funds
    0.41
    Big
    0.41
    University
    0.41
    Meet
    0.41
    Sparse
    0.41
    UInt
    0.40
    //$
    0.40
    Science
    0.40
    Activations Density 0.001%

    No Known Activations