© 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. 55554
    Prev
    Next
    INDEX
    Explanations

    point of, tab, member is

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

    explore, criteria, repeating

    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
    ,
    0.51
     actively
    0.49
    YPE
    0.48
     transporte
    0.48
    .
    0.45
     activa
    0.44
     ac
    0.44
     compart
    0.44
    -
    0.44
    EEP
    0.43
    POSITIVE LOGITS
    ಋ
    0.49
    अन्य
    0.48
    犮
    0.48
    SpacerItem
    0.48
    avacanam
    0.47
    buttonLevel
    0.46
    व्यक्तित्व
    0.46
     Bellingham
    0.46
    鋈
    0.45
    ഋ
    0.45
    Activations Density 0.000%

    No Known Activations