© 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. 84831
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
    。
    -1.53
    Hilsen
    -1.53
     not
    -1.48
    新
    -1.46
     musisz
    -1.45
    没
    -1.40
    częściej
    -1.38
     usually
    -1.38
    ।
    -1.38
    花
    -1.37
    POSITIVE LOGITS
     to
    2.13
     our
    1.58
    更大的
    1.55
    嚷
    1.49
     we
    1.47
     unſ
    1.41
     ſtate
    1.41
    同様に
    1.40
     you
    1.37
    蓓
    1.34
    Activations Density 0.073%

    No Known Activations