© 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. 65858
    Prev
    Next
    INDEX
    Explanations

    places or locations

    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
    </h3>
    -1.63
     Miß
    -1.42
    O
    -1.37
    **/
    -1.34
     and
    -1.34
     irgende
    -1.30
    “…
    -1.29
     its
    -1.27
    伃
    -1.27
    This
    -1.23
    POSITIVE LOGITS
    Otros
    1.58
     diğer
    1.49
     innych
    1.49
    Otras
    1.41
     다른
    1.38
     other
    1.38
    Aunque
    1.33
     khác
    1.33
    他にも
    1.33
     otras
    1.32
    Activations Density 0.069%

    No Known Activations