© 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. 32592
    Prev
    Next
    INDEX
    Explanations

    notification visibility information

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     harapan
    -0.76
     Leiter
    -0.73
    ficas
    -0.72
    }`}
    -0.70
    ㈢
    -0.69
    iterrane
    -0.69
     предпо
    -0.69
    不清
    -0.68
    sibilidad
    -0.68
     остав
    -0.68
    POSITIVE LOGITS
     telegram
    0.77
     православ
    0.76
     Neuron
    0.75
    gląd
    0.75
    Cohort
    0.75
     gypsy
    0.74
    NodeInfo
    0.73
    yorsunuz
    0.73
     самоу
    0.73
     ([]
    0.73
    Activations Density 0.012%

    No Known Activations