© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109824
    Prev
    Next
    INDEX
    Explanations

    active or selected 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_34/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
    Počet
    -0.86
    amá
    -0.81
     ancak
    -0.80
    就是一个
    -0.80
     undist
    -0.78
    Dimanche
    -0.78
     vacía
    -0.78
     Evento
    -0.77
    Consistent
    -0.77
     Consistent
    -0.76
    POSITIVE LOGITS
     active
    2.02
     current
    1.82
    active
    1.52
    ACTIVE
    1.35
     currently
    1.31
    current
    1.28
    当前
    1.25
     CURRENT
    1.23
     ACTIVE
    1.20
     selected
    1.20
    Activations Density 0.016%

    No Known Activations