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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8781
    Prev
    Next
    INDEX
    Explanations

    sph, ph, eph, aph prefixes

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific and biological terms with specific prefixes like "Aph", "Eph", and "Sph".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     something
    -0.84
     famously
    -0.82
     potential
    -0.81
     potentially
    -0.78
     Specifically
    -0.77
     formerly
    -0.76
    ellate
    -0.75
     specifically
    -0.74
     bepaald
    -0.74
     easily
    -0.73
    POSITIVE LOGITS
    sph
    0.96
    Ph
    0.84
     Madeline
    0.83
    isticated
    0.83
     maternity
    0.82
    یا
    0.81
     ราคา
    0.81
    Ἡ
    0.80
    celia
    0.79
    ph
    0.78
    Activations Density 0.073%

    No Known Activations