© 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. 10-GEMMASCOPE-RES-131K
    7. 59672
    Prev
    Next
    INDEX
    Explanations

    hat, hat is, hatches, hatful

    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_10/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
    vantaged
    -3.94
    gucig
    -3.30
    屃
    -3.16
    jewództ
    -3.11
    鹉
    -3.00
    öpfer
    -2.97
    ensions
    -2.84
    ondheim
    -2.81
    żli
    -2.78
    antism
    -2.72
    POSITIVE LOGITS
     BOTH
    3.52
    t
    3.30
    hat
    3.30
    s
    3.19
     
    3.11
    /
    3.05
    --
    3.02
    as
    2.94
    “
    2.89
    e
    2.81
    Activations Density 0.007%

    No Known Activations