© 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. 238826
    Prev
    Next
    INDEX
    Explanations

    product types and services

    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
     hedging
    0.46
    粗
    0.46
    วิธีการ
    0.45
     repairing
    0.44
     ruck
    0.43
    рама
    0.43
     countering
    0.43
     அவர்
    0.42
     растения
    0.42
     broom
    0.42
    POSITIVE LOGITS
    c
    0.55
    pas
    0.52
     Modes
    0.50
     Citizenship
    0.50
     Corp
    0.49
     Deck
    0.49
     Suits
    0.49
     Fuels
    0.48
     Cin
    0.48
     Popul
    0.48
    Activations Density 0.001%

    No Known Activations