© 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. 10-GEMMASCOPE-RES-131K
    7. 130134
    Prev
    Next
    INDEX
    Explanations

    TMZ, Society, rRNA, ET

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

    news and media organization names such as Times, Society, TMZ, and ET.

    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_10/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
    {
    -2.95
    ”—
    -1.95
     inquired
    -1.68
    \
    -1.66
    }?>
    -1.66
    g
    -1.66
    șit
    -1.65
    es
    -1.65
     $^{
    -1.63
     η
    -1.63
    POSITIVE LOGITS
    
    2.09
    ſſi
    2.03
    aimeJ
    1.98
    出来ます
    1.91
    嵓
    1.89
     spannende
    1.88
    쑹
    1.85
    
    1.83
    ௅
    1.82
    臈
    1.82
    Activations Density 0.009%

    No Known Activations