© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108771
    Prev
    Next
    INDEX
    Explanations

    structured questions and responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    7
    0.14
    S
    0.14
    ↵↵
    0.13
    <0xE3>
    0.13
    ↵
    0.13
    6
    0.13
    0.13
    R
    0.12
    T
    0.12
    D
    0.12
    POSITIVE LOGITS
     habitudes
    0.12
     bureaucratic
    0.12
     ഇത്തരം
    0.12
     économiques
    0.11
     intérêt
    0.11
     selfishness
    0.11
     problèmes
    0.11
     slogans
    0.11
     prerog
    0.11
     dissonance
    0.11
    Activations Density 0.000%

    No Known Activations