© 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. 10-GEMMASCOPE-RES-131K
    7. 112999
    Prev
    Next
    INDEX
    Explanations

    Spanish and English phrase beginnings

    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
    ↵
    -3.56
    饪
    -2.97
    那我
    -2.73
     xícara
    -2.69
    䊏
    -2.67
    葑
    -2.64
     этот
    -2.63
     setelan
    -2.45
    潆
    -2.45
    ᷆
    -2.42
    POSITIVE LOGITS
    providedIn
    3.02
     to
    2.88
    鯓
    2.83
     afar
    2.52
     celebrated
    2.38
     them
    2.34
     最高
    2.33
     gouverneur
    2.31
     biasanya
    2.31
    er
    2.31
    Activations Density 0.000%

    No Known Activations