© 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. 90150
    Prev
    Next
    INDEX
    Explanations

    location and type descriptors

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

    hypothetical questions and statements

    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
    
    0.48
     αρχ
    0.47
    ხვევ
    0.47
    дер
    0.46
    들은
    0.46
    forKey
    0.46
    
    0.46
     आयुक्त
    0.45
     கட
    0.45
    ３
    0.45
    POSITIVE LOGITS
     VIP
    0.48
     a
    0.46
    u
    0.46
    om
    0.45
     standalone
    0.44
     Vip
    0.43
     «
    0.43
     deletion
    0.43
     finisher
    0.43
     Beast
    0.42
    Activations Density 0.000%

    No Known Activations