© 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. 191913
    Prev
    Next
    INDEX
    Explanations

    professionals know about certification

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

    following `for`

    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
     działal
    0.54
    .|__
    0.53
     działalności
    0.53
     聞い
    0.53
     tomto
    0.52
     நடவடிக்கைகள்
    0.52
    ῷ
    0.51
     vitória
    0.49
     осигурање
    0.48
     активность
    0.48
    POSITIVE LOGITS
    ↵
    0.58
    len
    0.46
     adhesive
    0.46
    ↵↵
    0.46
    ent
    0.46
    ge
    0.45
    set
    0.45
    িপুর
    0.45
     edge
    0.45
    的
    0.45
    Activations Density 0.000%

    No Known Activations