© 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. 248280
    Prev
    Next
    INDEX
    Explanations

    groups or individuals

    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
     wirtschaft
    0.52
    ﾝ
    0.48
     jahr
    0.48
    ἴ
    0.47
     ELECTRO
    0.46
    licted
    0.45
     preis
    0.45
    鏝
    0.45
    gypte
    0.44
    íssimo
    0.44
    POSITIVE LOGITS
    amu
    0.38
     frees
    0.38
     takže
    0.38
    ?
    0.38
     investigated
    0.38
     truyện
    0.37
    frees
    0.37
     Hello
    0.37
    centers
    0.37
     اكتب
    0.37
    Activations Density 0.000%

    No Known Activations