© 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. 652
    Prev
    Next
    INDEX
    Explanations

    describing an effect

    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
    of
    -2.33
     valentín
    -2.03
     ۷
    -2.03
    would
    -2.00
     ۱۱
    -1.98
    ⩥
    -1.95
     mengubah
    -1.95
     ſaid
    -1.90
     esigen
    -1.87
     êtres
    -1.86
    POSITIVE LOGITS
    .
    2.11
     The
    1.84
     }
    1.84
     traditionelle
    1.81
    </em>
    1.80
    “
    1.80
     --
    1.78
    ſu
    1.77
     Vermögens
    1.77
     Tentang
    1.72
    Activations Density 0.103%

    No Known Activations