© 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-65K
    7. 30362
    Prev
    Next
    INDEX
    Explanations

    explaining or proposing proofs

    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_65k_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
    ain
    0.42
    3
    0.42
    2
    0.38
    uid
    0.37
    List
    0.37
    ins
    0.37
    adian
    0.37
    1
    0.37
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.36
    ere
    0.36
    POSITIVE LOGITS
    ของ
    0.36
     The
    0.33
     của
    0.33
     confertim
    0.33
    ವೇಂದ್ರ
    0.33
     aeron
    0.32
     perawatan
    0.32
     médicos
    0.32
     ndị
    0.32
     sông
    0.31
    Activations Density 0.186%

    No Known Activations