© 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. 31-GEMMASCOPE-2-RES-65K
    7. 9570
    Prev
    Next
    INDEX
    Explanations

    mathematical logarithm functions

    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_31_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
    0.52
     bey
    0.45
    lijn
    0.43
     V
    0.42
    leaved
    0.42
    line
    0.42
     reverse
    0.41
    lyn
    0.41
    reverse
    0.40
     berk
    0.40
    POSITIVE LOGITS
     fillColor
    0.45
    ambio
    0.44
    ెర
    0.44
    髂
    0.44
     ឬ
    0.43
     bottomRight
    0.42
    <unused662>
    0.41
    Painting
    0.41
    散射
    0.40
     frescoes
    0.40
    Activations Density 0.001%

    No Known Activations