© 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. 70623
    Prev
    Next
    INDEX
    Explanations

    p followed by punctuation or letters

    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
    ”
    -1.65
     how
    -1.53
    "
    -1.52
    ;
    -1.48
     get
    -1.42
     cannot
    -1.38
     was
    -1.36
    time
    -1.34
     to
    -1.32
     those
    -1.30
    POSITIVE LOGITS
     広場
    1.48
     Kø
    1.45
    Manfaat
    1.40
    blech
    1.40
     gestern
    1.39
    Salu
    1.38
    smh
    1.38
    Ǟ
    1.38
    sofa
    1.37
    ◆◇
    1.37
    Activations Density 0.009%

    No Known Activations