© 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. 232773
    Prev
    Next
    INDEX
    Explanations

    reports and official terms

    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
    的长
    0.48
    éré
    0.45
    øk
    0.45
    érant
    0.44
    GameOver
    0.44
     。
    0.43
    espère
    0.42
    équ
    0.42
    cheduling
    0.42
     configuración
    0.42
    POSITIVE LOGITS
     фирмы
    0.47
     caliber
    0.45
    ALSO
    0.44
     genu
    0.44
     pioneered
    0.44
     роман
    0.44
     calmness
    0.44
    店の
    0.43
    利
    0.43
    IRS
    0.43
    Activations Density 0.001%

    No Known Activations