Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8160
    Prev
    Next
    INDEX
    Explanations

    VI, variable, instrument, IEEE

    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
    JoinColumn
    -0.72
     токси
    -0.67
    Rage
    -0.66
     loạn
    -0.65
    TOX
    -0.64
     toxins
    -0.63
     Sarac
    -0.63
    არ
    -0.63
     DBG
    -0.63
     Rage
    -0.62
    POSITIVE LOGITS
     GP
    1.03
     IEEE
    1.01
     SCP
    1.00
     visa
    0.95
    IEEE
    0.92
     Visa
    0.90
    visa
    0.89
     query
    0.89
     instrument
    0.88
     Instrument
    0.87
    Activations Density 0.010%

    No Known Activations