© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90047
    Prev
    Next
    INDEX
    Explanations

    words starting with Ale

    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
    ப்
    -0.82
     Briefe
    -0.81
    ₙ
    -0.81
     occidentalis
    -0.80
    actually
    -0.79
     aranha
    -0.78
    usst
    -0.77
    ugd
    -0.76
     vun
    -0.76
    razos
    -0.76
    POSITIVE LOGITS
     Ale
    1.06
     Але
    1.04
    Ale
    1.01
     але
    0.88
     ALE
    0.82
     alleviate
    0.79
    Але
    0.78
     without
    0.77
     toured
    0.74
    Without
    0.73
    Activations Density 0.015%

    No Known Activations