© 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. 197692
    Prev
    Next
    INDEX
    Explanations

    level and its qualifiers

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

    level of detail or degree

    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
    ون
    1.09
    ים
    0.98
    на
    0.89
    る
    0.80
    ی
    0.80
    s
    0.79
    িন
    0.79
    َ
    0.73
    ের
    0.69
    ري
    0.69
    POSITIVE LOGITS
     nivel
    0.93
     LEVEL
    0.88
    其他
    0.85
     poziom
    0.84
    Level
    0.79
    '
    0.76
     düzey
    0.73
     level
    0.73
     уровнем
    0.73
     nivå
    0.71
    Activations Density 0.071%

    No Known Activations