© 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. 128547
    Prev
    Next
    INDEX
    Explanations

    lists and hierarchical 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
     visse
    -1.56
     fei
    -1.54
     alha
    -1.52
     riva
    -1.51
     tramont
    -1.51
     rusa
    -1.48
    🙈
    -1.47
     resa
    -1.46
     socc
    -1.44
     bambu
    -1.44
    POSITIVE LOGITS
     of
    1.75
    jusqu
    1.49
     verlieren
    1.45
    ،
    1.44
     empiezan
    1.43
     piensan
    1.38
     taper
    1.35
     ponen
    1.35
     möj
    1.34
     avec
    1.34
    Activations Density 0.019%

    No Known Activations