© 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. 110587
    Prev
    Next
    INDEX
    Explanations

    TG Tog T.G. TGCTs tgds

    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
     ○
    -0.79
    적으로
    -0.74
     dekat
    -0.72
     Corte
    -0.71
    sivamente
    -0.68
     antara
    -0.68
    dies
    -0.68
     Sentinel
    -0.67
     заря
    -0.67
    rages
    -0.66
    POSITIVE LOGITS
    Ether
    0.83
     worry
    0.81
     originais
    0.81
     trưng
    0.80
    ETHER
    0.79
    ☨
    0.73
     Tog
    0.73
     ursprünglichen
    0.72
    amarine
    0.72
    pertina
    0.72
    Activations Density 0.027%

    No Known Activations