© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73839
    Prev
    Next
    INDEX
    Explanations

    or Christopher Rojas

    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
    再び
    -0.93
     OGSÅ
    -0.91
     χρησιμοποι
    -0.88
    err
    -0.84
    INDUSTR
    -0.83
     jeweiligen
    -0.82
    iney
    -0.81
     '',
    -0.81
    歴代
    -0.80
     joyful
    -0.79
    POSITIVE LOGITS
     noget
    0.84
     OBITUARY
    0.82
    čí
    0.81
    Qw
    0.81
     едва
    0.78
    DataItem
    0.77
    Neuron
    0.75
    などなど
    0.75
     modulus
    0.75
    Jh
    0.75
    Activations Density 0.191%

    No Known Activations