© 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. 7862
    Prev
    Next
    INDEX
    Explanations

    half year-old

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

    life and soul

    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
    0.55
    وم
    0.53
     ساعات
    0.52
    ina
    0.49
    no
    0.49
    /
    0.49
    ova
    0.48
     يو
    0.48
     e
    0.48
    من
    0.48
    POSITIVE LOGITS
    Jlc
    0.55
     kepad
    0.53
     subordination
    0.52
    Ⲃ
    0.52
    価値
    0.50
     ആണ
    0.50
    CTOGRAM
    0.50
     correlate
    0.49
     sesize
    0.49
    かん
    0.48
    Activations Density 0.000%

    No Known Activations