© 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. 115438
    Prev
    Next
    INDEX
    Explanations

    import and image

    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
    przy
    -0.77
    giatan
    -0.76
    锦
    -0.74
    livia
    -0.73
    akti
    -0.73
     weights
    -0.73
    weighed
    -0.72
     STRO
    -0.71
     FIRE
    -0.68
     λ
    -0.68
    POSITIVE LOGITS
    Oferta
    0.81
    けれ
    0.68
    ăng
    0.67
    🛶
    0.67
     reassured
    0.65
    ldre
    0.65
     přek
    0.64
    ulu
    0.63
    MADRID
    0.62
     subdue
    0.62
    Activations Density 0.056%

    No Known Activations