© 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. 164439
    Prev
    Next
    INDEX
    Explanations

    design was

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

    listing items or facts

    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
    诶
    0.47
    Axes
    0.47
    داع
    0.46
    laughs
    0.45
    provider
    0.44
    <0xF4>
    0.43
    طل
    0.43
    ״
    0.43
    Author
    0.43
    Ej
    0.43
    POSITIVE LOGITS
     Mene
    0.50
     Fuzzy
    0.50
     cinq
    0.50
     volvió
    0.49
     Salle
    0.47
     Garner
    0.47
     Luz
    0.46
     Hao
    0.46
     Noct
    0.46
     Tabor
    0.46
    Activations Density 0.001%

    No Known Activations