© 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. 40-GEMMASCOPE-2-RES-262K
    7. 33735
    Prev
    Next
    INDEX
    Explanations

    yield return

    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_40_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
    urch
    0.41
    h
    0.39
     ill
    0.39
    am
    0.39
     fields
    0.39
    เจ
    0.37
    Supplementary
    0.36
    ched
    0.36
     Privilege
    0.36
    ill
    0.35
    POSITIVE LOGITS
     bremsstrahlung
    0.53
     breakage
    0.49
     bialgebra
    0.42
    GreaterThan
    0.42
    佹
    0.41
    笘
    0.41
     Krim
    0.41
     Crimea
    0.40
     broken
    0.40
    broken
    0.40
    Activations Density 0.000%

    No Known Activations