© 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. 800
    Prev
    Next
    INDEX
    Explanations

    junit tests

    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
    ρω
    -0.83
    izations
    -0.76
     Zugriff
    -0.74
     Replacement
    -0.74
    tamiento
    -0.74
     labios
    -0.74
     modulus
    -0.73
    Resistance
    -0.73
     Substituting
    -0.73
     대해
    -0.72
    POSITIVE LOGITS
    RunWith
    0.78
    まっている
    0.72
    ("@
    0.72
     scolaires
    0.71
    ylon
    0.71
    educ
    0.71
    клей
    0.71
     risk
    0.71
     può
    0.70
    fiction
    0.69
    Activations Density 0.009%

    No Known Activations