© 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. 3074
    Prev
    Next
    INDEX
    Explanations

    code formatting printing

    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
    fueled
    0.23
    ”
    0.22
     fueled
    0.21
    NUMBER
    0.21
    ##
    0.21
    <u>
    0.21
     —
    0.21
    I
    0.20
    calculations
    0.20
    MARINE
    0.20
    POSITIVE LOGITS
     presenceData
    0.26
    $&$-
    0.24
     vorhand
    0.24
     bekas
    0.24
     Anschließend
    0.23
    TrackAngle
    0.23
     selectInput
    0.23
    graphHead
    0.22
     principalTable
    0.22
     idha
    0.22
    Activations Density 0.297%

    No Known Activations