© 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. 16-GEMMASCOPE-2-RES-262K
    7. 144652
    Prev
    Next
    INDEX
    Explanations

    stands as

    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_16_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
     руху
    0.70
     badań
    0.63
     về
    0.60
     הס
    0.59
     investigação
    0.58
    ൮
    0.58
     invocation
    0.58
     fondness
    0.58
    ის
    0.57
    Ꮕ
    0.57
    POSITIVE LOGITS
    T
    0.75
    .
    0.60
    N
    0.60
    Jy
    0.59
    J
    0.58
     Gree
    0.57
    諧
    0.57
    don
    0.56
    Kv
    0.56
    lin
    0.55
    Activations Density 0.006%

    No Known Activations