© 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. 210084
    Prev
    Next
    INDEX
    Explanations

    particular gender

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

    VTuber, pixel art, metrics, entities, Shekels

    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
    槟
    0.53
     ẩm
    0.48
    ╽
    0.48
    ])).
    0.48
    न्नी
    0.47
     realizzazione
    0.47
    ेक्ट
    0.47
     کردی
    0.46
     hidrat
    0.45
    善良
    0.45
    POSITIVE LOGITS
    ון
    0.49
    学
    0.47
    ي
    0.47
    ный
    0.46
     claims
    0.43
    倒是
    0.43
     frequency
    0.43
     overturn
    0.42
    â
    0.41
    學
    0.41
    Activations Density 0.000%

    No Known Activations