© 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. 228576
    Prev
    Next
    INDEX
    Explanations

    folder, spreadsheet, marriage, space

    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
     Folding
    0.42
     Sporting
    0.42
     অন্যান্য
    0.40
     ITC
    0.39
     sculpting
    0.39
    x
    0.39
     DCs
    0.38
     hunting
    0.38
     sporting
    0.38
     Stati
    0.38
    POSITIVE LOGITS
    Renewal
    0.50
    當時
    0.49
     ตาม
    0.46
    Inicial
    0.46
     நடந்தது
    0.45
    िलासपुर
    0.45
    ตาม
    0.45
     बर्थ
    0.45
    𝟐
    0.45
     बवाल
    0.45
    Activations Density 0.005%

    No Known Activations