© 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. 9625
    Prev
    Next
    INDEX
    Explanations

    locations and structures

    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
     with
    -1.97
     more
    -1.94
     first
    -1.77
     also
    -1.55
     for
    -1.53
     einzigen
    -1.51
     and
    -1.49
     duidelijk
    -1.45
     part
    -1.44
     only
    -1.42
    POSITIVE LOGITS
    —
    1.42
     liquide
    1.35
     ferme
    1.34
     solide
    1.33
     humide
    1.28
     teste
    1.27
     annon
    1.26
     langer
    1.25
     gaf
    1.23
     complexe
    1.23
    Activations Density 0.124%

    No Known Activations