© 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. 181988
    Prev
    Next
    INDEX
    Explanations

    categories and car features

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

    json data and code configuration

    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
     vred
    0.50
    𒋛
    0.50
    Usu
    0.49
     tiende
    0.48
    ங்களுக்கும்
    0.48
     પ્રા
    0.47
     Teknik
    0.47
     beho
    0.47
     乳
    0.47
    AttributeInfo
    0.47
    POSITIVE LOGITS
     localisation
    0.45
    ignore
    0.45
    android
    0.43
    a
    0.43
    list
    0.42
    지만
    0.42
    ワンピース
    0.42
    ͋
    0.42
     metrics
    0.41
    VIEW
    0.41
    Activations Density 0.000%

    No Known Activations