© 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. 67639
    Prev
    Next
    INDEX
    Explanations

    organizations and institutions

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

    official, mandated, specific, lacking

    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
    integer
    0.46
     Consultado
    0.44
    和
    0.44
    Телефон
    0.43
    igno
    0.43
    3
    0.42
    category
    0.42
     বির
    0.42
     বিষয়
    0.42
    Z
    0.42
    POSITIVE LOGITS
     fotos
    0.50
     Missions
    0.48
     eben
    0.46
     Monsoon
    0.46
     refurbishment
    0.45
     картины
    0.45
     Photos
    0.44
     itulah
    0.44
     aslında
    0.44
     mă
    0.43
    Activations Density 0.000%

    No Known Activations