© 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. 156949
    Prev
    Next
    INDEX
    Explanations

    between you and custom fittings

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

    functional descriptions

    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
    isse
    0.47
    H
    0.47
    oski
    0.47
     Issa
    0.46
    ৮
    0.46
    M
    0.46
    ”
    0.46
     করিবার
    0.45
    一口
    0.44
    خة
    0.44
    POSITIVE LOGITS
     продъл
    0.46
     socialization
    0.45
    }=-\
    0.44
    funct
    0.44
    }=-
    0.42
    getic
    0.42
     Crum
    0.41
    战士
    0.41
     functional
    0.41
     सोशल
    0.41
    Activations Density 0.001%

    No Known Activations