© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8944
    Prev
    Next
    INDEX
    Explanations

    numerical and code structures

    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_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
    Util
    0.43
     Werk
    0.41
     গে
    0.39
     చేస్తున్న
    0.39
    6
    0.39
    ６
    0.38
     Temmuz
    0.38
     ৬
    0.37
     प्रयोग
    0.37
    ("{
    0.37
    POSITIVE LOGITS
    ées
    0.52
     начинают
    0.49
    ット
    0.45
    rees
    0.44
    stion
    0.44
    aiset
    0.42
    ista
    0.42
    anée
    0.42
     நாம்
    0.41
    駅
    0.41
    Activations Density 0.003%

    No Known Activations