© 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. 109646
    Prev
    Next
    INDEX
    Explanations

    knobs, dials, and rotation

    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
    strando
    -0.78
    PLEMENT
    -0.76
     polis
    -0.76
    astos
    -0.74
     Wic
    -0.74
    結婚
    -0.73
    tekend
    -0.73
     campana
    -0.72
    kembangkan
    -0.71
     aldehyde
    -0.71
    POSITIVE LOGITS
     knob
    2.81
     dial
    2.73
     knobs
    2.17
     dials
    2.14
    dial
    1.99
     rotary
    1.95
    knob
    1.94
     Dial
    1.91
    Dial
    1.77
     Knob
    1.73
    Activations Density 0.031%

    No Known Activations