© 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. 34-GEMMASCOPE-RES-131K
    7. 31095
    Prev
    Next
    INDEX
    Explanations

    incrementing operators and code constructs

    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
    (--
    -1.04
     ensalada
    -0.82
    мото
    -0.82
     Organics
    -0.80
    AVIA
    -0.78
     navnet
    -0.78
     lycée
    -0.77
    führende
    -0.76
     gavetas
    -0.75
     лв
    -0.75
    POSITIVE LOGITS
    ++]
    1.21
    ++
    1.09
    ++)
    0.83
    ‰
    0.82
    Which
    0.78
    ?,
    0.75
     [],
    0.75
    出張
    0.75
    []
    0.74
    lação
    0.74
    Activations Density 0.006%

    No Known Activations