© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 14325
    Prev
    Next
    INDEX
    Explanations

    binary form

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers in text (numeric tokens)

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    -1.23
    確認ください
    -1.12
    pení
    -1.10
    corrhi
    -1.10
     agarre
    -1.09
    телей
    -1.09
     PÅ
    -1.09
    ات
    -1.06
     even
    -1.06
     från
    -1.05
    POSITIVE LOGITS
    もあって
    1.16
    と思っている
    1.14
    と思っていた
    1.12
    所以在
    1.09
    axaca
    1.07
    という感じ
    1.02
    があり
    1.02
    除此之外
    1.02
     ailing
    1.02
    了一個
    0.99
    Activations Density 0.067%

    No Known Activations