© 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. 163711
    Prev
    Next
    INDEX
    Explanations

    list items separated by commas

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

    variations and roles

    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
     VEL
    0.49
    lit
    0.48
     I
    0.47
    er
    0.47
     ("
    0.46
     Lei
    0.46
    lily
    0.46
     incidents
    0.46
     In
    0.45
     Events
    0.45
    POSITIVE LOGITS
     oscuridad
    0.54
    ्यूम
    0.49
     esperando
    0.49
    ImageQueue
    0.47
    नीय
    0.47
    उसके
    0.47
    KeyboardMarkup
    0.46
    اع
    0.46
    ول
    0.45
    했
    0.45
    Activations Density 0.001%

    No Known Activations