© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58210
    Prev
    Next
    INDEX
    Explanations

    into abstract destinations

    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
     into
    -1.28
    以上就是
    -1.08
     to
    -1.00
     évaluation
    -0.89
    動機
    -0.88
    機種
    -0.88
    仕事の
    -0.83
     dodging
    -0.81
    手に入
    -0.80
    しかも
    -0.80
    POSITIVE LOGITS
     perpetuity
    1.08
     infinity
    1.04
     eternity
    1.00
    xic
    0.98
     adulthood
    0.97
     oblivion
    0.96
    üş
    0.92
    ⲉ
    0.87
     obscurity
    0.87
    軽減
    0.85
    Activations Density 0.021%

    No Known Activations