© 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. 7006
    Prev
    Next
    INDEX
    Explanations

    code, paths, dialogue, descriptions

    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
    ivar
    -0.78
    իս
    -0.77
    ությ
    -0.77
    endalikan
    -0.76
    ながら
    -0.74
    脚下
    -0.72
     vzduchu
    -0.71
    \}$
    -0.71
    nachweise
    -0.70
    but
    -0.69
    POSITIVE LOGITS
    setTypeface
    0.84
     unit
    0.84
     Haush
    0.84
    UNITS
    0.83
     Units
    0.82
    ltä
    0.80
    Deskripsi
    0.79
    bracht
    0.78
    ỗng
    0.76
    liez
    0.76
    Activations Density 0.000%

    No Known Activations