© 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. 21471
    Prev
    Next
    INDEX
    Explanations

    code structures

    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
    欤
    0.46
     werkt
    0.45
    .$,
    0.44
     ermög
    0.43
    ర్థిక
    0.42
     эсеп
    0.41
     まとめ
    0.40
     '.',
    0.40
     편리
    0.40
     தலைமைய
    0.39
    POSITIVE LOGITS
    ه
    0.56
    0
    0.49
    উনি
    0.45
     entertainment
    0.43
     nostalgia
    0.43
    Influ
    0.43
    ना
    0.42
     Influ
    0.42
    ালে
    0.42
     Invention
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.