© 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. 242452
    Prev
    Next
    INDEX
    Explanations

    inside or origin

    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
    oliberal
    0.47
    ábamos
    0.45
    elenggarakan
    0.45
    umar
    0.44
     дописа
    0.44
    墠
    0.44
    فرنس
    0.44
    ivanje
    0.43
    stopwords
    0.43
    umni
    0.43
    POSITIVE LOGITS
    )}+\
    0.46
    子
    0.44
    食
    0.44
     dalam
    0.43
    補助
    0.42
    บุ
    0.42
    ใน
    0.41
     در
    0.41
     ಕು
    0.41
     ಆಹಾರ
    0.41
    Activations Density 0.000%

    No Known Activations