© 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. 16389
    Prev
    Next
    INDEX
    Explanations

    property visible

    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
    匯
    0.46
    אה
    0.43
     IANS
    0.40
     Rechts
    0.40
     berkata
    0.39
     kết
    0.39
     स्वातंत्र
    0.39
     settled
    0.39
     रहमान
    0.39
     funda
    0.38
    POSITIVE LOGITS
    𝓹
    0.45
     offices
    0.45
     ಆರೋಗ್ಯ
    0.45
     Дні
    0.44
     ዓይ
    0.42
     validations
    0.42
     పరుగులు
    0.42
    \}$.
    0.42
    이에요
    0.41
    ຕ້ອງການ
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.