© 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. 64930
    Prev
    Next
    INDEX
    Explanations

    participants starting, services listed, 4 W/E

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

    fecha de

    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
    EH
    0.52
     recognized
    0.50
    0.48
    IR
    0.45
     recognizable
    0.45
     V
    0.44
    AV
    0.44
     colored
    0.44
     Erk
    0.42
    eh
    0.42
    POSITIVE LOGITS
    ásticas
    0.55
     گی
    0.52
    ци
    0.49
    Ἡ
    0.48
     γρα
    0.48
     oposición
    0.48
    闷
    0.48
     menores
    0.47
     teorías
    0.47
    niers
    0.46
    Activations Density 0.000%

    No Known Activations