© 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. 20907
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
     schild
    -1.54
    .*")]
    -1.47
    both
    -1.45
    medriver
    -1.44
     hemd
    -1.42
    走进
    -1.40
    cilia
    -1.38
    zystać
    -1.36
    ÇÕES
    -1.35
     Púb
    -1.33
    POSITIVE LOGITS
    ↵↵
    2.02
     or
    1.57
    0
    1.49
    j
    1.42
    z
    1.42
    e
    1.40
    );
    1.40
     menschlichen
    1.39
    i
    1.38
    ou
    1.38
    Activations Density 0.004%

    No Known Activations