© 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. 203082
    Prev
    Next
    INDEX
    Explanations

    decision-making contexts following specific words

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

    a description of a state

    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
     अन
    0.48
    笄
    0.48
    일상
    0.46
    DAILY
    0.46
     Inorg
    0.46
     ежеднев
    0.45
    algar
    0.45
    肌
    0.45
    がい
    0.44
     vải
    0.44
    POSITIVE LOGITS
    ্লাহ
    0.50
     nimmt
    0.47
     millimeter
    0.46
    یدر
    0.46
     interpretive
    0.45
     hilfre
    0.45
     stalwart
    0.45
    علن
    0.45
     nonprofit
    0.44
     metropolitan
    0.44
    Activations Density 0.000%

    No Known Activations