© 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. 54403
    Prev
    Next
    INDEX
    Explanations

    foreign characters and specific phrases

    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
     धर्म
    0.52
    Age
    0.51
     예
    0.48
     Orphan
    0.48
    m
    0.48
    aps
    0.47
     Workshop
    0.46
     యే
    0.46
     imprecise
    0.46
    ap
    0.45
    POSITIVE LOGITS
    ِي
    0.45
    SPEED
    0.43
    ofstream
    0.43
     carénés
    0.42
    нула
    0.41
    ன்
    0.41
    Commenting
    0.41
    ودي
    0.41
    BtnUp
    0.40
    ي
    0.40
    Activations Density 0.020%

    No Known Activations