© 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. 26288
    Prev
    Next
    INDEX
    Explanations

    company and brand 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
    ふと
    -1.08
     their
    -1.05
     ospiti
    -1.01
    に入れる
    -1.00
     intitu
    -0.98
     giud
    -0.96
     suon
    -0.95
    дах
    -0.95
     Their
    -0.95
     comuni
    -0.94
    POSITIVE LOGITS
    がありますが
    1.22
    <bos>
    1.19
     часть
    1.16
    ของ
    1.08
     of
    1.06
     của
    1.05
     של
    1.02
    もあります
    1.00
     část
    0.99
    があります
    0.98
    Activations Density 0.181%

    No Known Activations