© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64214
    Prev
    Next
    INDEX
    Explanations

    words starting with ach

    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
     yii
    -0.78
     zune
    -0.75
    風格
    -0.75
     Максим
    -0.75
    喜歡的
    -0.72
     Ceiling
    -0.71
     применяется
    -0.71
     Barker
    -0.70
     edif
    -0.69
    もはや
    -0.69
    POSITIVE LOGITS
     ach
    0.83
     Ach
    0.81
    Ach
    0.75
    ʁ
    0.75
     ache
    0.74
     Oasis
    0.73
     NEVER
    0.73
    XMLSchema
    0.72
    彩
    0.72
    绿
    0.71
    Activations Density 0.017%

    No Known Activations