© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109839
    Prev
    Next
    INDEX
    Explanations

    improved quality, reduced costs

    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
    ıy
    0.42
    five
    0.42
    ernos
    0.42
     बीमार
    0.41
    ided
    0.40
    throat
    0.40
    需
    0.40
    cutoff
    0.40
    defining
    0.40
     eight
    0.39
    POSITIVE LOGITS
     людей
    0.45
     Able
    0.45
     espiritual
    0.44
     Menschen
    0.43
     religious
    0.43
     espirit
    0.43
     своей
    0.42
    这个人
    0.41
     remission
    0.41
    驭
    0.41
    Activations Density 0.002%

    No Known Activations