© 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-65K
    7. 2271
    Prev
    Next
    INDEX
    Explanations

    b or B followed by words

    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_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
    nością
    0.42
    ności
    0.38
    Instances
    0.36
    ຯ
    0.36
     উঁচু
    0.35
     등으로
    0.34
    柣
    0.34
     Fresnel
    0.34
     FERC
    0.34
    க்கார
    0.33
    POSITIVE LOGITS
     B
    0.90
     b
    0.89
    B
    0.73
    autiful
    0.57
    b
    0.57
     bland
    0.56
    haviour
    0.54
     Better
    0.54
     బ
    0.53
    <0x99>
    0.53
    Activations Density 0.178%

    No Known Activations