© 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. 116421
    Prev
    Next
    INDEX
    Explanations

    time and academic subjects

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

    efficiency, goals, or benefits

    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
    moon
    0.55
    ppard
    0.54
    cherry
    0.54
    }=\
    0.53
    hed
    0.53
    hander
    0.50
    heiro
    0.49
    fted
    0.48
    opatra
    0.48
    byn
    0.48
    POSITIVE LOGITS
    烁
    0.53
    İM
    0.46
     Dant
    0.46
    ە
    0.45
     Calculus
    0.45
     Courses
    0.45
    课
    0.44
    کہ
    0.44
     ụ
    0.44
     мі
    0.43
    Activations Density 0.000%

    No Known Activations