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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10586
    Prev
    Next
    INDEX
    Explanations

    words ending in er or eer

    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_10/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
     }
    -2.22
     —
    -2.11
     другие
    -2.09
    絎
    -2.05
     Mehrheit
    -2.05
     l
    -1.94
    倏
    -1.89
    …。
    -1.87
    ^{*}$
    -1.86
    游戏的
    -1.86
    POSITIVE LOGITS
    h
    2.39
    ";
    2.25
    逦
    2.11
    獁
    2.08
    (
    2.08
    発売
    2.08
    {
    2.03
    嵛
    1.98
    喼
    1.95
    硨
    1.94
    Activations Density 0.013%

    No Known Activations