© 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. 209036
    Prev
    Next
    INDEX
    Explanations

    additional annual, center field, one week

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

    characteristics of things

    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
    ão
    0.50
    uy
    0.50
    ultures
    0.50
    recovery
    0.50
    i
    0.50
    healing
    0.49
    joy
    0.49
    4
    0.49
    봉
    0.49
    hell
    0.48
    POSITIVE LOGITS
     Blazer
    0.46
    toLocale
    0.46
     невозможно
    0.45
     КАК
    0.44
     юго
    0.44
     не
    0.43
    WithPath
    0.43
     noc
    0.43
     сем
    0.43
     idha
    0.43
    Activations Density 0.000%

    No Known Activations