© 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. 91524
    Prev
    Next
    INDEX
    Explanations

    unsuccessful attempts

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

    The main thing this neuron does is detect numerical tokens (any digits or numbers, such as years, counts, or other numeric values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    justed
    -0.77
    غول
    -0.75
    øm
    -0.75
    farers
    -0.74
    lared
    -0.74
    ENI
    -0.74
     hamil
    -0.73
    ัล
    -0.73
    zilla
    -0.72
    Revenir
    -0.71
    POSITIVE LOGITS
     unsuccessful
    4.97
     unsuccessfully
    4.19
     fruitless
    2.70
     безу
    2.67
     erfol
    2.47
     неу
    2.20
     futile
    2.20
    Uns
    2.13
     Uns
    2.11
     failed
    2.05
    Activations Density 0.125%

    No Known Activations