© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27246
    Prev
    Next
    INDEX
    Explanations

    compound nouns or specifications

    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_22/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
    lė
    -1.41
     indien
    -1.27
     dépens
    -1.26
    औ
    -1.25
     betaling
    -1.22
    ŗ
    -1.22
    عبد
    -1.20
     fossero
    -1.20
     Bakan
    -1.20
    edade
    -1.19
    POSITIVE LOGITS
    I
    1.24
    H
    1.21
    n
    1.19
     presentará
    1.13
     unfairly
    1.13
    ).
    1.11
    K
    1.11
    Y
    1.09
     in
    1.08
     Kommentare
    1.08
    Activations Density 0.230%

    No Known Activations