© 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. 252001
    Prev
    Next
    INDEX
    Explanations

    promoted or became

    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
    專輯
    0.52
     ofrecemos
    0.49
     or
    0.48
    鍗
    0.48
    Ofer
    0.45
    畩
    0.44
     education
    0.44
    कुछ
    0.44
    ค
    0.44
    dm
    0.43
    POSITIVE LOGITS
    önt
    0.50
    ])));
    0.50
    ysta
    0.49
    ylim
    0.47
    ordano
    0.46
    uedata
    0.44
     Кре
    0.42
    Missense
    0.42
     xuân
    0.42
    <unused53>
    0.42
    Activations Density 0.000%

    No Known Activations