© 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. 155596
    Prev
    Next
    INDEX
    Explanations

    locations, regions, and values

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

    describing state or importance

    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
     utensils
    0.50
     meals
    0.47
    নেস
    0.46
    飢
    0.43
    渐
    0.42
    懇
    0.42
    ないので
    0.42
    ければ
    0.41
     blindness
    0.41
    िन्
    0.41
    POSITIVE LOGITS
    AY
    0.55
    ㄿ
    0.55
     SUB
    0.51
     DATE
    0.50
     BAY
    0.50
     Continued
    0.49
     ENGLISH
    0.49
     поступи
    0.49
     MEAS
    0.48
     FINANCIAL
    0.48
    Activations Density 0.000%

    No Known Activations