© 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. 14393
    Prev
    Next
    INDEX
    Explanations

    textbooks and related queries

    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
    </td>
    -3.30
    }
    -2.55
    撄
    -2.52
     "
    -2.48
     was
    -2.47
     $^{
    -2.34
     její
    -2.33
    ?
    -2.19
     \
    -2.17
    istocene
    -2.13
    POSITIVE LOGITS
    You
    2.73
     increasing
    2.61
    when
    2.53
    珢
    2.52
     упаковке
    2.45
    If
    2.41
    there
    2.34
    塤
    2.33
     נוסף
    2.33
     numerosos
    2.33
    Activations Density 0.002%

    No Known Activations