© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83616
    Prev
    Next
    INDEX
    Explanations

    image suggestion

    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
    にくい
    0.48
     refuted
    0.48
    ्रिक
    0.48
     FEBRUARY
    0.47
     critic
    0.47
     }^{
    0.47
     ವರ್ಷ
    0.46
     Фургал
    0.46
    🇾
    0.45
    溆
    0.44
    POSITIVE LOGITS
    To
    0.54
    L
    0.54
    R
    0.54
    Give
    0.53
    Be
    0.52
    Complete
    0.52
    Press
    0.52
    As
    0.51
    Counsel
    0.51
    Raw
    0.50
    Activations Density 0.002%

    No Known Activations