© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85832
    Prev
    Next
    INDEX
    Explanations

    ridiculous, absurd, silly

    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
     für
    -1.76
     säga
    -1.70
    鉿
    -1.63
     coloriage
    -1.62
     prenda
    -1.62
     is
    -1.61
     blanda
    -1.59
    饧
    -1.56
    텝
    -1.53
    nocení
    -1.52
    POSITIVE LOGITS
    ness
    1.93
    1
    1.90
     grüne
    1.81
    .
    1.63
     comienzan
    1.59
    ity
    1.59
     blaue
    1.58
    ztő
    1.57
    麪
    1.52
    りました
    1.51
    Activations Density 0.012%

    No Known Activations