© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 12164
    Prev
    Next
    INDEX
    Explanations

    license and cause

    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
    atillo
    -0.77
    woch
    -0.71
    saus
    -0.71
    tifie
    -0.70
    lernen
    -0.70
    φέ
    -0.70
    crafting
    -0.69
    Defect
    -0.68
    چھ
    -0.68
     鼠
    -0.68
    POSITIVE LOGITS
    ℝ
    0.69
     نه
    0.69
     Lips
    0.69
    histogram
    0.68
    guid
    0.68
     воде
    0.67
     Jesucristo
    0.66
    áb
    0.65
     filter
    0.63
    g
    0.63
    Activations Density 0.062%

    No Known Activations