© 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. 67017
    Prev
    Next
    INDEX
    Explanations

    radio frequencies (AM/FM/TV)

    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
     حتی
    -1.70
     that
    -1.63
    x
    -1.57
    ps
    -1.38
     even
    -1.34
    ⇨
    -1.32
     then
    -1.30
     incluso
    -1.30
     peluche
    -1.23
    '])
    -1.23
    POSITIVE LOGITS
    koala
    1.59
     plezier
    1.43
     của
    1.38
     rozwoju
    1.37
    redmi
    1.36
    ratulations
    1.35
     preferido
    1.33
    箩
    1.32
     verdieping
    1.29
     bezoek
    1.27
    Activations Density 0.036%

    No Known Activations