© 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-65K
    7. 3582
    Prev
    Next
    INDEX
    Explanations

    constrained word starters

    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_65k_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
    을
    0.55
     ауди
    0.46
     vibrate
    0.42
     acoustics
    0.41
    ُول
    0.41
    了
    0.41
    닝
    0.41
    ות
    0.41
    API
    0.41
     formatting
    0.40
    POSITIVE LOGITS
     Somebody
    0.42
     असंख्य
    0.42
     Below
    0.41
     Does
    0.41
     なる
    0.39
     Apakah
    0.39
     શું
    0.39
    every
    0.39
     DefaultTargets
    0.39
     Почему
    0.38
    Activations Density 0.020%

    No Known Activations