© 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. 40-GEMMASCOPE-2-RES-262K
    7. 10413
    Prev
    Next
    INDEX
    Explanations

    css style declarations

    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
    onnés
    0.39
    📝
    0.39
     Canvas
    0.38
     Pisa
    0.37
    Canvas
    0.37
     Aisha
    0.36
     محبوب
    0.36
     رم
    0.36
    旎
    0.36
    角落
    0.35
    POSITIVE LOGITS
     visibility
    0.66
    visibility
    0.59
     float
    0.52
     {'
    0.47
     Visibility
    0.47
    vnd
    0.44
    float
    0.43
     position
    0.42
    Css
    0.42
     vertical
    0.42
    Activations Density 0.012%

    No Known Activations