© 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-16K
    7. 11917
    Prev
    Next
    INDEX
    Explanations

    at a certain rate

    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_16k_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
    PanelVisual
    0.45
    ος
    0.43
    itipi
    0.43
     ಪೂರ್ವ
    0.42
    GBuf
    0.41
    FreeFlag
    0.41
     balcon
    0.41
    豢
    0.41
    Hence
    0.41
     වන
    0.40
    POSITIVE LOGITS
     an
    0.46
     a
    0.41
     Classes
    0.38
     Rage
    0.38
     constant
    0.37
     dan
    0.37
     rage
    0.36
     RMS
    0.36
     Opp
    0.36
    -
    0.35
    Activations Density 0.019%

    No Known Activations