© 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. 60624
    Prev
    Next
    INDEX
    Explanations

    hinge

    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
    γραφία
    -0.80
     niedriger
    -0.77
     ceilings
    -0.75
    lecture
    -0.74
    adaptor
    -0.73
    来到了
    -0.71
     mouth
    -0.71
     uitzicht
    -0.71
    Geology
    -0.70
     micrófono
    -0.70
    POSITIVE LOGITS
     hinges
    3.16
     hinge
    2.97
     Hinge
    2.03
     Hing
    1.88
    hing
    1.65
    hin
    1.61
    HING
    1.60
     hing
    1.59
     hinged
    1.52
    hinged
    1.41
    Activations Density 0.028%

    No Known Activations