© 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. 22-GEMMASCOPE-RES-131K
    7. 27122
    Prev
    Next
    INDEX
    Explanations

    first person accounts

    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
     is
    -1.02
    i
    -1.01
     当前
    -1.01
    もちろん
    -0.99
     TAMBÉM
    -0.98
     представ
    -0.94
     к
    -0.93
     operativos
    -0.92
    "
    -0.91
     其他
    -0.90
    POSITIVE LOGITS
    Ꮸ
    1.09
     jakieś
    1.09
     zrobić
    1.06
     crisi
    1.03
     кілька
    1.02
    mäßigen
    1.01
    Angebot
    1.01
     vacas
    0.99
    Fonto
    0.98
    ッテリー
    0.98
    Activations Density 0.042%

    No Known Activations