© 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. 65592
    Prev
    Next
    INDEX
    Explanations

    d

    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
    nought
    -0.91
    cipal
    -0.76
    colat
    -0.76
    profit
    -0.73
    ustering
    -0.73
    nothing
    -0.73
    allets
    -0.73
    image
    -0.72
    obia
    -0.72
    nast
    -0.72
    POSITIVE LOGITS
     February
    0.81
     although
    0.79
     October
    0.76
     Although
    0.75
     July
    0.73
     January
    0.72
     considers
    0.71
     Philharmonic
    0.70
    يلة
    0.69
     different
    0.69
    Activations Density 0.016%

    No Known Activations