© 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. 34-GEMMASCOPE-RES-131K
    7. 108804
    Prev
    Next
    INDEX
    Explanations

    special characters and code identifiers

    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_34/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
    tranh
    -1.11
    cautions
    -0.96
     ngừa
    -0.95
     veranderen
    -0.94
    ございません
    -0.93
     predominance
    -0.92
    sculpture
    -0.90
    sufficiency
    -0.88
     zobac
    -0.88
    𝙳
    -0.88
    POSITIVE LOGITS
    がある
    1.17
    各样的
    1.16
    often
    1.16
    were
    1.14
    菒
    1.12
    ("
    1.10
    sometimes
    1.10
     elegantly
    1.06
     wacky
    1.04
    尽管
    1.03
    Activations Density 0.123%

    No Known Activations