© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67051
    Prev
    Next
    INDEX
    Explanations

    despise / despised / despicable creature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    屃
    -3.02
    噚
    -2.67
    🩻
    -2.58
    縂
    -2.44
     různých
    -2.41
    งิน
    -2.41
    ズニー
    -2.41
     Hinblick
    -2.39
    ครื่อง
    -2.36
     而
    -2.36
    POSITIVE LOGITS
    2
    3.81
    3
    3.67
    9
    3.63
    0
    3.47
    1
    3.17
    7
    3.16
    5
    3.11
    *
    3.08
    <
    2.95
    8
    2.80
    Activations Density 0.012%

    No Known Activations