© 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. 151979
    Prev
    Next
    INDEX
    Explanations

    front facing camera

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

    problems, negative states, or specific components

    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
    :
    0.59
     placent
    0.46
     arz
    0.43
     calorías
    0.42
     abbreviations
    0.42
    :+
    0.42
     lambs
    0.42
     ejercicios
    0.41
     ஏக்க
    0.39
     guides
    0.39
    POSITIVE LOGITS
     そして
    0.59
    ScheduledAction
    0.54
    SendCommand
    0.52
     chiave
    0.51
    selectTable
    0.49
    CommandBuffer
    0.48
    eseen
    0.46
     ເ
    0.46
    Src
    0.46
     thấy
    0.44
    Activations Density 0.000%

    No Known Activations