© 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. 59475
    Prev
    Next
    INDEX
    Explanations

    programming class or biological class

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

    terms related to programming or software class designations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    猡
    -2.88
    餿
    -2.73
    榘
    -2.63
     tivesse
    -2.59
     disfru
    -2.59
    瑨
    -2.58
    𝄆
    -2.48
    姤
    -2.47
    udière
    -2.45
    蓥
    -2.45
    POSITIVE LOGITS
    2
    4.88
    9
    4.16
    3
    4.16
    7
    3.73
    5
    3.73
    _
    3.58
    In
    3.56
    A
    3.56
    0
    3.55
    8
    3.48
    Activations Density 0.073%

    No Known Activations