© 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. 116916
    Prev
    Next
    INDEX
    Explanations

    spin, spinning, misdirection, evasion

    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
    ISME
    -0.82
    IMENT
    -0.80
    кля
    -0.77
    ꜜ
    -0.75
    侵
    -0.73
     осу
    -0.73
     superstition
    -0.71
     exacting
    -0.71
    桟
    -0.71
     stupid
    -0.70
    POSITIVE LOGITS
     spin
    1.60
    spin
    1.59
     spinning
    1.42
    Spin
    1.39
     dising
    1.30
     Spin
    1.30
     spins
    1.27
     evasion
    1.23
     SPIN
    1.20
     twisting
    1.18
    Activations Density 0.057%

    No Known Activations