© 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. 34-GEMMASCOPE-RES-131K
    7. 119132
    Prev
    Next
    INDEX
    Explanations

    pos, Pres, Pos, Zas, Nas, посо + lan, lov, lav, tel, ov, led, ano, nys

    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_34/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
     teng
    -0.98
    '}';
    -0.93
    becoming
    -0.84
    developing
    -0.81
    گزاری
    -0.81
    haling
    -0.80
    piratory
    -0.80
    halation
    -0.79
    quickly
    -0.77
     roślin
    -0.76
    POSITIVE LOGITS
    dá
    0.80
    هر
    0.78
     Owls
    0.78
    rere
    0.75
    lé
    0.75
    服务
    0.73
    德
    0.72
    Только
    0.69
    tivism
    0.69
    setTexture
    0.69
    Activations Density 0.008%

    No Known Activations