© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25771
    Prev
    Next
    INDEX
    Explanations

    ionization, reproduction, colonization

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

    terms related to mass spectrometry and ionization techniques in scientific contexts.

    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
     real
    -0.86
     residence
    -0.85
    Real
    -0.81
    orale
    -0.75
    ATELY
    -0.73
    用户
    -0.71
    ОР
    -0.70
    мку
    -0.70
    าหล
    -0.69
    ार
    -0.69
    POSITIVE LOGITS
    makeup
    0.82
     Scripps
    0.75
     Agric
    0.74
    ')";
    0.72
     mão
    0.72
     affirmative
    0.71
    ',...
    0.71
    Giveaway
    0.71
     Locus
    0.71
     Preview
    0.71
    Activations Density 0.041%

    No Known Activations