© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 666
    Prev
    Next
    INDEX
    Explanations

    traveler or traveller

    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
    '
    -2.92
     '
    -2.80
    </strong>
    -2.66
    </em>
    -2.64
     perfekte
    -2.56
     marvelous
    -2.50
    }{
    -2.47
    -
    -2.39
     perverse
    -2.31
     The
    -2.30
    POSITIVE LOGITS
     détaillée
    2.91
    栳
    2.61
    there
    2.55
    [...,
    2.53
    ),),
    2.48
    骓
    2.41
    ﺶ
    2.36
     betrek
    2.36
    酹
    2.33
     They
    2.31
    Activations Density 0.004%

    No Known Activations