© 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. 34-GEMMASCOPE-RES-131K
    7. 81230
    Prev
    Next
    INDEX
    Explanations

    mouse events and company identifiers

    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
    🦘
    -0.82
     Oceania
    -0.81
    ponse
    -0.74
    inh
    -0.73
    становка
    -0.71
     Response
    -0.70
     ini
    -0.70
     response
    -0.70
    tifiable
    -0.70
    <0xBA>
    -0.68
    POSITIVE LOGITS
    拢
    0.71
    шов
    0.70
     tolerated
    0.69
    enton
    0.66
    フィル
    0.65
    そ
    0.64
    Differ
    0.64
    logies
    0.63
     pathologist
    0.63
     coincided
    0.63
    Activations Density 0.036%

    No Known Activations