© 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. 22-GEMMASCOPE-RES-131K
    4. 14945
    Prev
    Next
    INDEX
    Explanations

    HTML tags and close characters

    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_22/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
     to
    -1.61
     that
    -1.40
     for
    -1.15
     Pristupljeno
    -1.14
     after
    -1.14
    فاق
    -1.10
     this
    -1.06
    :
    -1.05
     since
    -1.05
     rusak
    -1.03
    POSITIVE LOGITS
    そして
    1.23
    <bos>
    1.19
    時間は
    1.09
     lastly
    1.02
    などが
    1.01
    と
    0.95
     finally
    0.94
     Behaup
    0.94
    は
    0.94
     incluso
    0.94
    Activations Density 0.003%

    No Known Activations