© 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. 22-GEMMASCOPE-RES-131K
    7. 16178
    Prev
    Next
    INDEX
    Explanations

    tech news and specific names

    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_22/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
     ■
    -0.91
     sahaja
    -0.91
     with
    -0.85
     have
    -0.81
    ヶ
    -0.80
     könnten
    -0.80
     nonverbal
    -0.79
     придется
    -0.79
    ↵↵↵↵↵↵↵↵
    -0.77
     trat
    -0.76
    POSITIVE LOGITS
    јани
    1.12
     caixas
    0.86
     Trace
    0.86
    aternity
    0.85
     csoport
    0.84
    ल्ड
    0.83
    YNAM
    0.82
    𝓞
    0.82
    ساخت
    0.82
    cây
    0.81
    Activations Density 0.003%

    No Known Activations