© 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. 22-GEMMASCOPE-RES-131K
    7. 14141
    Prev
    Next
    INDEX
    Explanations

    array manipulation

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

    The neuron flags numeric literals (numbers and constants) in code or technical text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     kabát
    -0.94
    Havolalar
    -0.91
    ším
    -0.87
    cím
    -0.85
     climático
    -0.84
     yako
    -0.84
     Konkur
    -0.83
    }/*
    -0.83
    iele
    -0.82
    landers
    -0.82
    POSITIVE LOGITS
     namorado
    0.83
     Guin
    0.82
    得点
    0.82
     incluyendo
    0.81
     英語
    0.81
     serviço
    0.81
    tivos
    0.80
     преподава
    0.80
     diagnosed
    0.79
     lựa
    0.79
    Activations Density 0.092%

    No Known Activations