© 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. 66767
    Prev
    Next
    INDEX
    Explanations

    serious modification

    np_acts-logits-general · gemini-2.5-flash-lite

    the noun or noun phrase immediately following the adjective “serious.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Ᏹ
    -1.71
    ти
    -1.67
    ‌‌
    -1.63
    噥
    -1.60
    м
    -1.60
    ши
    -1.59
    阚
    -1.58
     ?$
    -1.57
     dañ
    -1.55
     cheering
    -1.55
    POSITIVE LOGITS
     poważ
    1.87
    0
    1.67
     zelfs
    1.56
    this
    1.53
    ly
    1.48
    <bos>
    1.47
     ciddi
    1.47
     któ
    1.45
     of
    1.43
    はこの
    1.43
    Activations Density 0.022%

    No Known Activations