© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 55452
    Prev
    Next
    INDEX
    Explanations

    accessing `.value`

    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
    ้ง
    0.36
     och
    0.36
    জু
    0.35
    幷
    0.35
     Го
    0.35
    门
    0.35
     황
    0.35
     ví
    0.34
    ધ
    0.34
    并且
    0.34
    POSITIVE LOGITS
    VALUE
    0.51
    value
    0.46
     VALUE
    0.45
     value
    0.45
     waarde
    0.44
    Value
    0.44
    toNumber
    0.43
     Value
    0.43
    tolist
    0.42
    iobium
    0.41
    Activations Density 0.029%

    No Known Activations