© 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. 82972
    Prev
    Next
    INDEX
    Explanations

    sticks, wands, rods, poles

    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
    🦱
    -0.84
    ස
    -0.72
     μη
    -0.72
    聒
    -0.71
     começar
    -0.70
    cnf
    -0.70
    кас
    -0.69
    acimiento
    -0.69
     gasket
    -0.69
    asties
    -0.69
    POSITIVE LOGITS
     sticks
    2.48
     stick
    2.33
    stick
    1.93
    sticks
    1.89
     Sticks
    1.85
    Stick
    1.80
     Stick
    1.77
    棒
    1.75
     rod
    1.71
     pole
    1.70
    Activations Density 0.040%

    No Known Activations