© 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. 183480
    Prev
    Next
    INDEX
    Explanations

    your family

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

    brain organizes knowledge

    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
    iint
    0.51
    در
    0.50
     int
    0.48
     in
    0.47
    ↵
    0.45
     intima
    0.44
     IP
    0.43
     intellectuals
    0.42
    ****************
    0.42
     setups
    0.42
    POSITIVE LOGITS
    сног
    0.59
     выбирать
    0.53
     пур
    0.52
    ினார்
    0.52
     находи
    0.51
     Николай
    0.50
     плохо
    0.50
     Вулкан
    0.50
    тни
    0.49
     леген
    0.49
    Activations Density 0.000%

    No Known Activations