© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106711
    Prev
    Next
    INDEX
    Explanations

    expressions of intensity or comparison

    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
     Camus
    -0.79
    คม
    -0.76
    Wig
    -0.70
     DAB
    -0.70
    きたいと思います
    -0.69
     撮
    -0.69
     awarding
    -0.68
    hijo
    -0.68
    дание
    -0.66
    ضة
    -0.66
    POSITIVE LOGITS
     crazy
    2.16
    crazy
    1.70
    Crazy
    1.52
     mad
    1.49
     wildfire
    1.38
     Crazy
    1.27
     CRA
    1.19
     nobody
    1.08
     MAD
    1.02
     whoa
    1.02
    Activations Density 0.038%

    No Known Activations