© 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. 99841
    Prev
    Next
    INDEX
    Explanations

    referred to

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

    The neuron is primarily detecting occurrences of the digit “1” (i.e. whenever the token “1” appears).

    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
     водо
    -0.82
     xv
    -0.79
     alia
    -0.75
     utilizzati
    -0.74
     nito
    -0.73
    Já
    -0.73
     چ
    -0.73
     devenir
    -0.72
     hl
    -0.71
     غ
    -0.70
    POSITIVE LOGITS
    吋
    0.84
    鎹
    0.81
    uktur
    0.79
     tuyến
    0.78
    өздер
    0.77
     lipstick
    0.75
    렴
    0.74
     programmer
    0.73
    idemiology
    0.73
     Programmer
    0.72
    Activations Density 0.008%

    No Known Activations