© 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. 201694
    Prev
    Next
    INDEX
    Explanations

    metrics, operations, or warning

    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
    𝐢
    0.52
    𝐱
    0.52
     Israël
    0.51
    ない
    0.50
    t
    0.49
     professed
    0.48
     Seaside
    0.48
    L
    0.47
    vár
    0.47
     rencontres
    0.47
    POSITIVE LOGITS
     полного
    0.42
    erts
    0.42
    Съ
    0.42
     কোনটা
    0.40
    çado
    0.40
    τσ
    0.39
     فشار
    0.39
     מט
    0.39
    ften
    0.39
     συνο
    0.39
    Activations Density 0.001%

    No Known Activations