© 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. 251578
    Prev
    Next
    INDEX
    Explanations

    account number

    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
     blurred
    0.50
     aberta
    0.47
     OBJECTTYPE
    0.47
    ಲಿದೆ
    0.46
     gadis
    0.45
     queried
    0.45
    궐
    0.45
    情報は
    0.44
     roasted
    0.44
    ঘাট
    0.44
    POSITIVE LOGITS
    il
    0.70
    it
    0.61
    ang
    0.59
    ing
    0.59
    kl
    0.58
    ü
    0.57
    ،
    0.55
    ig
    0.55
    im
    0.54
    Rek
    0.54
    Activations Density 0.000%

    No Known Activations