© 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. 53860
    Prev
    Next
    INDEX
    Explanations

    numbered list item `1)`

    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
     Website
    0.44
    4
    0.43
    ponsored
    0.41
    facebook
    0.40
    tega
    0.40
    Website
    0.40
    7
    0.40
    エイ
    0.39
    ptor
    0.39
    8
    0.39
    POSITIVE LOGITS
     контек
    0.43
     навыки
    0.43
    RatingDiff
    0.42
     результаты
    0.40
    ப்பட்ட
    0.38
     корне
    0.38
     względu
    0.38
    ᚕ
    0.37
    зге
    0.37
    CCE
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.