© 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. 95958
    Prev
    Next
    INDEX
    Explanations

    both or either

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

    various types

    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
    HEAD
    0.50
    タ
    0.49
     relays
    0.47
    JA
    0.47
    CH
    0.47
     relay
    0.46
    HL
    0.45
    KA
    0.45
    JE
    0.45
    OH
    0.45
    POSITIVE LOGITS
    yatiti
    0.53
     Abr
    0.50
    䒺
    0.49
     тяжело
    0.48
     Gabriella
    0.48
     Persia
    0.47
    اردوشاعری
    0.46
    prar
    0.46
     жизни
    0.46
     Francesca
    0.46
    Activations Density 0.000%

    No Known Activations