© 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. 48162
    Prev
    Next
    INDEX
    Explanations

    integrals

    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
     menschliche
    -1.67
     now
    -1.65
     choice
    -1.53
     menschlichen
    -1.48
     used
    -1.48
     üblichen
    -1.47
     piú
    -1.45
     ausdrück
    -1.45
     gegenwär
    -1.44
     sometimes
    -1.41
    POSITIVE LOGITS
    wegen
    1.63
     any
    1.52
     BOTH
    1.49
     all
    1.46
     ANYTHING
    1.45
    LAUGHTER
    1.37
     sonore
    1.34
    ngulo
    1.34
     anz
    1.33
     июня
    1.33
    Activations Density 0.016%

    No Known Activations