© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108696
    Prev
    Next
    INDEX
    Explanations

    chemical formulas with strontium

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

    chemical formulas and notation for compounds with subscripts and numerical values.

    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
     September
    -0.94
     during
    -0.92
     even
    -0.89
     despite
    -0.89
     or
    -0.88
     خوردن
    -0.88
    Even
    -0.84
     found
    -0.84
     Even
    -0.82
     Though
    -0.80
    POSITIVE LOGITS
    Replace
    1.04
     $_{
    1.00
     Bibliography
    0.88
     maniere
    0.86
     Erdoğan
    0.85
     grumpy
    0.85
    Fibonacci
    0.85
    Records
    0.85
    }_{
    0.84
    <sub>
    0.84
    Activations Density 0.028%

    No Known Activations