© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61502
    Prev
    Next
    INDEX
    Explanations

    comparisons using auxiliary verbs

    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
     only
    -1.82
     тільки
    -1.34
    これだけ
    -1.31
     olmad
    -1.29
     сожалению
    -1.27
    Oleh
    -1.20
    体調
    -1.20
    Hanya
    -1.20
    Only
    -1.20
     лі
    -1.16
    POSITIVE LOGITS
     otras
    1.74
     of
    1.63
    ...........
    1.53
    <td>
    1.50
     outras
    1.49
     -
    1.47
     OTHER
    1.43
     Other
    1.43
    ----
    1.42
     It
    1.41
    Activations Density 0.026%

    No Known Activations