© 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. 5687
    Prev
    Next
    INDEX
    Explanations

    describing attributes or purpose

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

    abstract concepts and relationships

    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
     Moż
    0.33
    ക്കുന്ന
    0.30
    することは
    0.30
    取り組み
    0.30
     luggage
    0.30
     retaliation
    0.29
    <start_of_image>
    0.28
    どちら
    0.28
    <unused2125>
    0.28
    とても
    0.27
    POSITIVE LOGITS
     που
    0.64
    that
    0.62
     الذي
    0.60
     nécessaire
    0.57
     që
    0.56
     alluded
    0.55
     that
    0.55
     که
    0.53
     mentioned
    0.52
     التي
    0.52
    Activations Density 0.469%

    No Known Activations