© 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. 963
    Prev
    Next
    INDEX
    Explanations

    past actions and states

    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
     ۲۰۱
    -1.61
     currently
    -1.48
     their
    -1.44
     now
    -1.38
     got
    -1.38
     this
    -1.37
     already
    -1.31
     it
    -1.31
     started
    -1.30
     begins
    -1.27
    POSITIVE LOGITS
     to
    1.65
    da
    1.63
     of
    1.42
    Its
    1.38
    rightarrow
    1.38
    riment
    1.33
     molte
    1.30
     mélang
    1.28
     sadece
    1.27
     veröffentlicht
    1.27
    Activations Density 0.133%

    No Known Activations