© 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. 85666
    Prev
    Next
    INDEX
    Explanations

    proper nouns like 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_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
    μαστε
    -2.63
    ྜ
    -2.45
    嵎
    -2.36
    嘤
    -2.34
    ίων
    -2.33
    缫
    -2.33
     aparición
    -2.30
     felizes
    -2.28
     baratos
    -2.25
     colocación
    -2.22
    POSITIVE LOGITS
     Ensuring
    3.03
     เมื่อ
    2.72
    I
    2.67
     Mainly
    2.61
     Roughly
    2.59
     Easily
    2.59
     Exactly
    2.59
    ኧ
    2.58
     He
    2.55
     Extending
    2.53
    Activations Density 0.031%

    No Known Activations