© 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. 549
    Prev
    Next
    INDEX
    Explanations

    describing styles and subjects

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

    qualities and styles

    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
     halfCanvas
    0.25
    <unused2155>
    0.25
     debugDocument
    0.24
    <unused2197>
    0.23
     punctato
    0.23
     일반적으로
    0.23
     प्रत्येक
    0.23
    <unused1646>
    0.23
    ると
    0.22
    <unused985>
    0.22
    POSITIVE LOGITS
    -
    0.34
     vibes
    0.33
     mentality
    0.29
     tinge
    0.29
     vibe
    0.28
     themed
    0.28
     style
    0.28
     sensibility
    0.27
    气息
    0.27
    inspired
    0.26
    Activations Density 0.913%

    No Known Activations