© 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. 34845
    Prev
    Next
    INDEX
    Explanations

    cam and valve operation

    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
    verhältnis
    -0.87
     Statutory
    -0.79
     கூ
    -0.71
     πυ
    -0.71
    Dap
    -0.71
     метода
    -0.71
    ceres
    -0.68
    adalajara
    -0.66
     Visions
    -0.65
    Acro
    -0.64
    POSITIVE LOGITS
     cam
    1.98
    cam
    1.71
     cams
    1.59
     duration
    1.52
     Cam
    1.52
    Cam
    1.40
    duration
    1.37
     CAM
    1.34
    Duration
    1.34
     DUR
    1.33
    Activations Density 0.011%

    No Known Activations