© 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. 238051
    Prev
    Next
    INDEX
    Explanations

    core idea, VisualVM, Pip shouted

    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
     وين
    0.48
    </i>
    0.46
     tvrd
    0.46
     avant
    0.45
    を超
    0.44
     destro
    0.43
     sebelum
    0.43
     promet
    0.43
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.42
     d
    0.42
    POSITIVE LOGITS
    uddle
    0.50
    ittings
    0.47
    ક્ટ
    0.47
    ಲ್ಲು
    0.47
    tta
    0.46
    zeiten
    0.45
    蛳
    0.45
    backing
    0.45
    lectual
    0.45
    hangi
    0.45
    Activations Density 0.000%

    No Known Activations