© 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. 115838
    Prev
    Next
    INDEX
    Explanations

    you may

    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
    ボックス
    -0.72
    Reversed
    -0.71
    ticion
    -0.68
    っ
    -0.68
    ????????????????
    -0.65
    ficulty
    -0.64
    ipy
    -0.63
    argon
    -0.63
    piel
    -0.62
     checkbox
    -0.62
    POSITIVE LOGITS
    olan
    0.80
     Jow
    0.76
    ❸
    0.74
    omethane
    0.73
    說話
    0.73
    ientos
    0.71
    Build
    0.68
    言语
    0.66
    clin
    0.66
    ową
    0.66
    Activations Density 0.097%

    No Known Activations