© 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. 118863
    Prev
    Next
    INDEX
    Explanations

    condition or state of things

    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
    тивні
    -0.83
    órm
    -0.80
     chaleur
    -0.78
    ötzlich
    -0.75
    żym
    -0.72
     التطبيق
    -0.71
    StructField
    -0.70
    ㊁
    -0.70
     Relativity
    -0.70
    ява
    -0.70
    POSITIVE LOGITS
     condition
    6.03
    condition
    4.38
     состояние
    4.09
     Condition
    4.09
    Condition
    3.80
     state
    3.72
    状態
    3.45
     CONDITION
    3.44
     Zustand
    3.41
     estado
    3.33
    Activations Density 0.097%

    No Known Activations