© 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. 671
    Prev
    Next
    INDEX
    Explanations

    sensitization

    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
     “
    -2.78
     extremadamente
    -2.16
     utilizada
    -2.13
     accompanying
    -2.06
     versatility
    -2.05
    ).
    -2.03
    哢
    -2.02
     .”
    -1.96
    攫
    -1.93
     sanguí
    -1.92
    POSITIVE LOGITS
    which
    2.14
    Eight
    2.06
    itiert
    1.98
     Sensi
    1.96
    ."
    1.90
     you
    1.90
     θ
    1.85
    沨
    1.84
    \
    1.84
     \{
    1.83
    Activations Density 0.006%

    No Known Activations