© 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. 128043
    Prev
    Next
    INDEX
    Explanations

    filled with

    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
    fraud
    0.44
     instrument
    0.42
    탉
    0.42
    ра
    0.42
     quand
    0.41
    ह्
    0.41
     boundary
    0.40
     musician
    0.40
     proš
    0.40
    ชี
    0.39
    POSITIVE LOGITS
    ”:
    0.47
     enjo
    0.43
     相
    0.43
     तालुका
    0.43
     sillä
    0.43
     ન
    0.43
    noscript
    0.42
    ।''
    0.42
    𝗘
    0.42
    枌
    0.42
    Activations Density 0.001%

    No Known Activations