© 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. 33593
    Prev
    Next
    INDEX
    Explanations

    code block start or natural language context

    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
     from
    -1.27
     are
    -0.91
     Fett
    -0.85
    ggars
    -0.82
     manufacturer
    -0.82
     geographical
    -0.81
    طط
    -0.81
     Fieber
    -0.81
     starting
    -0.81
     existing
    -0.81
    POSITIVE LOGITS
    ऐ
    0.95
    兴奋
    0.94
     этого
    0.94
    衝
    0.89
    Boa
    0.88
     был
    0.85
     elast
    0.84
    没有
    0.84
    ณา
    0.84
    ワンピース
    0.84
    Activations Density 0.003%

    No Known Activations