© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 32665
    Prev
    Next
    INDEX
    Explanations

    abbreviations and punctuation

    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_34/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
    》。
    -1.21
     this
    -1.12
     Fällen
    -1.06
     different
    -1.03
    erdin
    -0.98
    This
    -0.98
     and
    -0.96
     following
    -0.96
    郵
    -0.95
     distintas
    -0.94
    POSITIVE LOGITS
    .,
    3.25
    ./
    2.63
    .-
    2.33
    .;
    2.27
    .'
    1.93
    .:
    1.90
    .),
    1.88
    .);
    1.88
    .',
    1.86
    .=
    1.79
    Activations Density 0.185%

    No Known Activations