© 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. 134602
    Prev
    Next
    INDEX
    Explanations

    nothing major

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

    code directives and comments

    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
     ફર
    0.49
    ur
    0.48
    irana
    0.45
    u
    0.45
     could
    0.44
    raction
    0.44
     Branson
    0.44
    ikannya
    0.43
    issy
    0.42
    디오
    0.42
    POSITIVE LOGITS
     nå
    0.51
    Biografia
    0.46
    سكر
    0.44
    Heute
    0.41
    誕
    0.41
    寶寶
    0.40
    捨
    0.40
     pern
    0.40
     nunc
    0.40
     beslut
    0.40
    Activations Density 0.002%

    No Known Activations