© 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. 53-GEMMASCOPE-2-RES-262K
    7. 39958
    Prev
    Next
    INDEX
    Explanations

    companies and launches

    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_53_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
    Chol
    0.42
     lossless
    0.41
    chol
    0.40
     Chol
    0.40
     chol
    0.40
    Sorting
    0.39
    烜
    0.39
    лас
    0.38
     threes
    0.38
    Las
    0.37
    POSITIVE LOGITS
     adheres
    0.40
    judice
    0.38
     stigma
    0.37
     slips
    0.37
    spir
    0.37
     Serb
    0.37
    feel
    0.36
     stems
    0.36
     dictates
    0.35
    扡
    0.35
    Activations Density 0.001%

    No Known Activations