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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143994
    Prev
    Next
    INDEX
    Explanations

    keeping your, often over

    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
    S
    0.54
    -
    0.54
    4
    0.54
    Y
    0.51
     will
    0.50
    T
    0.50
    :
    0.49
    K
    0.49
    司
    0.49
    C
    0.49
    POSITIVE LOGITS
    ныгы
    0.56
     solvation
    0.53
     vasculature
    0.52
     sinusoidal
    0.52
     elution
    0.52
     traversing
    0.51
    ूटूथ
    0.51
     equilibration
    0.50
     dupatta
    0.50
     phytochemical
    0.50
    Activations Density 0.006%

    No Known Activations