© 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-262K
    7. 12103
    Prev
    Next
    INDEX
    Explanations

    styles, breeds, language, Mega Evolution

    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_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
    <0xA6>
    0.38
    ispens
    0.38
     Energ
    0.36
     energ
    0.35
     supplier
    0.35
    Verified
    0.35
    reib
    0.35
     zonder
    0.35
    pper
    0.35
    ´
    0.34
    POSITIVE LOGITS
     Specimens
    0.47
     உள்ளட
    0.46
     Styles
    0.43
     оттен
    0.40
    व्यक्तित्व
    0.39
     '*',
    0.38
     styles
    0.38
    तो
    0.38
     Año
    0.38
    蘚
    0.38
    Activations Density 0.000%

    No Known Activations