© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75239
    Prev
    Next
    INDEX
    Explanations

    . followed by a word

    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
     often
    -1.12
     may
    -1.10
     never
    -1.05
    on
    -1.03
     have
    -1.00
     generally
    -0.98
     having
    -0.97
    новен
    -0.95
     not
    -0.94
    focusable
    -0.93
    POSITIVE LOGITS
    を選択します
    1.28
    ようですが
    1.22
    に似
    1.20
    に変更
    1.16
    ără
    1.13
     but
    1.11
    conut
    1.09
     and
    1.06
    ならでは
    1.06
    ほうが
    1.05
    Activations Density 0.075%

    No Known Activations