© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 168559
    Prev
    Next
    INDEX
    Explanations

    Google paid support elections

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

    enterprise issues or data

    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
    irt
    0.49
    ೇಕ
    0.48
    롬
    0.47
    Colour
    0.47
    ید
    0.46
    ちなみに
    0.45
    тья
    0.45
    '){$
    0.45
    rix
    0.44
    ements
    0.44
    POSITIVE LOGITS
     ache
    0.57
     mao
    0.54
     enterprises
    0.52
     entertainers
    0.52
     entreprise
    0.52
     entertainer
    0.50
     métier
    0.50
     war
    0.50
     auth
    0.49
     kultur
    0.49
    Activations Density 0.001%

    No Known Activations