© 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. 27502
    Prev
    Next
    INDEX
    Explanations

    class MYPROJECT_API

    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
    ỡng
    0.49
    愺
    0.43
    полнение
    0.42
     więks
    0.41
    泬
    0.40
     sufferings
    0.40
    楍
    0.40
    ዎችን
    0.39
     larger
    0.39
    ဝင်
    0.39
    POSITIVE LOGITS
     XXI
    0.44
     ба
    0.42
     гро
    0.41
     BAU
    0.40
     DASH
    0.39
     Conventions
    0.39
     Common
    0.38
    当代
    0.38
     History
    0.37
    H
    0.37
    Activations Density 0.000%

    No Known Activations