© 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. 74548
    Prev
    Next
    INDEX
    Explanations

    interface

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

    verification of manual changes

    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
     `./
    0.53
     linkages
    0.49
    πτυ
    0.49
    اونلو
    0.48
     embossing
    0.47
    geschoss
    0.47
     சொந்த
    0.47
     OXIDES
    0.47
     MODELS
    0.46
     oxidative
    0.46
    POSITIVE LOGITS
    ik
    0.49
    Av
    0.48
    (
    0.48
    回避
    0.48
    Maximum
    0.46
    at
    0.46
    US
    0.45
    вей
    0.45
    ×
    0.44
    Common
    0.44
    Activations Density 0.000%

    No Known Activations