© 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. 10-GEMMASCOPE-RES-131K
    7. 8582
    Prev
    Next
    INDEX
    Explanations

    LaTeX math environments

    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
    felves
    -1.95
    <td>
    -1.95
    rangle
    -1.88
    皷
    -1.88
     recensione
    -1.87
     mindset
    -1.83
    uiente
    -1.82
    躥
    -1.78
    rigs
    -1.76
     inverno
    -1.73
    POSITIVE LOGITS
    1
    2.00
     είναι
    1.83
    '
    1.81
     those
    1.78
     \&
    1.66
     was
    1.61
    *,
    1.58
     \
    1.54
     in
    1.53
     with
    1.52
    Activations Density 0.000%

    No Known Activations