© 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. 34-GEMMASCOPE-RES-131K
    4. 110559
    Prev
    Next
    INDEX
    Explanations

    names ending in ger

    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
    時間も
    -0.79
     abject
    -0.74
     różnych
    -0.73
    佢
    -0.73
    vapor
    -0.73
    valuation
    -0.72
    正常的
    -0.71
     concre
    -0.71
     Nop
    -0.71
    绑
    -0.71
    POSITIVE LOGITS
     enthalpy
    0.79
     labios
    0.77
     Aseg
    0.77
    Bv
    0.77
     muchos
    0.75
    länder
    0.74
    λίου
    0.74
    BCF
    0.73
    reactive
    0.73
     Asegúrese
    0.73
    Activations Density 0.023%

    No Known Activations