© 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. 78549
    Prev
    Next
    INDEX
    Explanations

    hats and headwear

    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
    りで
    -0.84
    bolt
    -0.84
    ल्स
    -0.78
     Fuerza
    -0.77
    ​​​​​​​
    -0.77
    𝗋
    -0.75
     Weich
    -0.75
    bolts
    -0.74
     GILBERT
    -0.73
    septic
    -0.72
    POSITIVE LOGITS
     hat
    3.50
     hats
    3.48
    Hat
    2.48
    hats
    2.41
     Hats
    2.39
     Hat
    2.30
    hat
    2.25
    帽子
    2.20
     HAT
    2.16
    Hats
    2.13
    Activations Density 0.021%

    No Known Activations