© 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-16K
    7. 6219
    Prev
    Next
    INDEX
    Explanations

    input details recommendations information features

    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
     уйнагыз
    0.36
    이
    0.33
    збеки
    0.33
     общения
    0.33
     которые
    0.32
    фан
    0.32
     социального
    0.32
    ０
    0.32
     конкур
    0.32
    мати
    0.31
    POSITIVE LOGITS
     a
    0.33
     are
    0.33
     box
    0.33
     není
    0.32
     merupakan
    0.31
     water
    0.30
     earth
    0.30
     sodium
    0.29
     reverb
    0.29
     muzzle
    0.29
    Activations Density 0.201%

    No Known Activations