© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 118845
    Prev
    Next
    INDEX
    Explanations

    measuring and assessing

    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
    Instead
    -1.49
     católica
    -1.47
    呈现
    -1.46
     hermosos
    -1.38
    價格
    -1.33
     Когда
    -1.31
     trasero
    -1.30
    撅
    -1.29
     Wartawan
    -1.29
     externas
    -1.29
    POSITIVE LOGITS
     with
    2.38
     for
    1.91
     of
    1.85
     in
    1.80
     when
    1.65
     if
    1.56
     on
    1.49
     using
    1.45
     where
    1.42
     not
    1.41
    Activations Density 0.278%

    No Known Activations