© 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. 127199
    Prev
    Next
    INDEX
    Explanations

    introducing examples

    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
    鲧
    -1.67
    indicates
    -1.56
    …(
    -1.49
     acheter
    -1.48
    齶
    -1.48
    䛗
    -1.47
    ateľ
    -1.47
    χύ
    -1.43
    鋦
    -1.41
    읭
    -1.40
    POSITIVE LOGITS
     as
    2.72
     of
    2.70
     and
    2.02
     with
    1.78
     into
    1.74
     a
    1.68
     at
    1.68
     in
    1.63
     to
    1.62
     A
    1.59
    Activations Density 0.172%

    No Known Activations