© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65392
    Prev
    Next
    INDEX
    Explanations

    I do not want to

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

    The neuron is detecting non-standard formatting characters (e.g. unusual whitespace or control symbols) rather than normal letters or digits.

    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
     spru
    -1.85
    Composición
    -1.70
    is
    -1.51
    liegende
    -1.48
    她
    -1.47
     只
    -1.45
    as
    -1.45
     这
    -1.44
    鉆
    -1.43
    很
    -1.41
    POSITIVE LOGITS
     each
    1.92
     Einrichtungen
    1.78
     a
    1.72
     pełni
    1.71
     atractivos
    1.70
    alakip
    1.70
     acuerdos
    1.66
     publicaciones
    1.66
     maravill
    1.66
     hermosos
    1.61
    Activations Density 0.002%

    No Known Activations