© 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. 223725
    Prev
    Next
    INDEX
    Explanations

    items or variations

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

    def, echo, all, severe, trauma

    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
    ’
    0.49
     anymore
    0.47
    !’
    0.46
    üğ
    0.45
    分別
    0.45
    (";
    0.44
    üğünüz
    0.44
     overlapping
    0.44
    分别
    0.44
    !';
    0.43
    POSITIVE LOGITS
     കൊ
    0.47
     ಆತ್ಮ
    0.46
     Nak
    0.45
    সম্মত
    0.45
     よる
    0.45
     Koe
    0.43
    篠
    0.43
     cuidados
    0.43
    RowFilter
    0.42
     Ko
    0.42
    Activations Density 0.001%

    No Known Activations