© 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-262K
    7. 23082
    Prev
    Next
    INDEX
    Explanations

    list operations

    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
    \{(
    0.50
     arrayOf
    0.44
     $\{(
    0.44
     Array
    0.43
    {(
    0.42
     wyt
    0.41
    彫
    0.40
    心が
    0.40
    ケル
    0.39
     {(
    0.38
    POSITIVE LOGITS
    [:]
    0.73
     extending
    0.66
     extend
    0.60
     extension
    0.59
    =[]
    0.59
    extend
    0.57
     extends
    0.56
     extender
    0.56
     extensions
    0.55
    ([])
    0.55
    Activations Density 0.028%

    No Known Activations