© 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. 108624
    Prev
    Next
    INDEX
    Explanations

    origin or source

    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
    IdList
    -0.96
    Glitter
    -0.76
    ี้ย
    -0.75
    iscono
    -0.75
    ᵂ
    -0.74
    <{
    -0.73
    istanbul
    -0.73
    Audrey
    -0.72
     Schmuck
    -0.72
     Giuliani
    -0.72
    POSITIVE LOGITS
     originality
    0.90
     Matching
    0.90
     correct
    0.88
     wartime
    0.86
     markings
    0.85
     faker
    0.84
     matching
    0.84
     Characteristics
    0.84
     Naval
    0.83
    matching
    0.82
    Activations Density 0.014%

    No Known Activations