© 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. 110830
    Prev
    Next
    INDEX
    Explanations

    travel and direction

    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
     zwarte
    -1.63
    ¡¡
    -1.56
    lijkse
    -1.56
    ,**
    -1.56
    ing
    -1.53
     hunne
    -1.49
     gouden
    -1.48
     laajenta
    -1.47
     suiker
    -1.47
     zijne
    -1.45
    POSITIVE LOGITS
     into
    2.25
     between
    2.00
     around
    1.86
     across
    1.70
     about
    1.64
    The
    1.59
     like
    1.58
     literally
    1.55
     Teile
    1.54
     through
    1.46
    Activations Density 0.042%

    No Known Activations