© 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. 64058
    Prev
    Next
    INDEX
    Explanations

    identify, absurd, complaint, referring, brief, players

    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
    s
    0.59
    g
    0.55
     work
    0.54
     disputes
    0.50
    fl
    0.50
     despatch
    0.48
    etera
    0.48
    Response
    0.48
     scaffolding
    0.47
     dispute
    0.47
    POSITIVE LOGITS
    秙
    0.50
     منٹو
    0.47
    叶
    0.47
    枼
    0.47
     foglie
    0.45
    вані
    0.45
     stockno
    0.45
    栲
    0.44
    uyentes
    0.44
    늑
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.