© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56907
    Prev
    Next
    INDEX
    Explanations

    years and dates

    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
    Negative Logits
     may
    -0.84
    ukų
    -0.81
     sector
    -0.79
    𝘀
    -0.76
    ᅟ
    -0.75
    Seq
    -0.75
    Printf
    -0.73
    されます
    -0.72
     πολι
    -0.71
     Like
    -0.70
    POSITIVE LOGITS
     skú
    0.93
    etz
    0.91
    𝕌
    0.84
     }=
    0.79
    MSD
    0.78
    sikan
    0.77
    ここで
    0.77
    mittags
    0.76
    IsNotEmpty
    0.76
    ksan
    0.76
    Activations Density 0.002%

    No Known Activations