© 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-16K
    7. 9998
    Prev
    Next
    INDEX
    Explanations

    case sensitivity and capitalization

    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_16k_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
    ソル
    0.39
    }(-
    0.38
    ahankan
    0.37
    ติ
    0.36
    îtes
    0.35
    ӵ
    0.35
    }=$
    0.34
    ಚಾರ
    0.34
    豫
    0.34
    ⠄
    0.34
    POSITIVE LOGITS
     uppercase
    2.16
     lowercase
    2.08
     capitalization
    2.02
     capital
    1.98
     capitalized
    1.98
     Capital
    1.94
    Capital
    1.92
     capitalize
    1.88
    Lowercase
    1.88
    Uppercase
    1.81
    Activations Density 0.272%

    No Known Activations