© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78689
    Prev
    Next
    INDEX
    Explanations

    apoptosis and bacteria

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

    technical or mathematical documentation keywords like "parameter", "description", or "definition".

    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
    Vem
    -0.93
     Länder
    -0.88
     information
    -0.84
     people
    -0.83
    prestige
    -0.80
     only
    -0.79
    ftone
    -0.79
     Herrn
    -0.77
     which
    -0.77
     or
    -0.77
    POSITIVE LOGITS
     chaînes
    0.84
    گ
    0.82
     bedankt
    0.81
     клави
    0.81
     eliminated
    0.80
    ')";
    0.79
    Queen
    0.77
    มา
    0.76
     combinatorial
    0.76
    IsOptional
    0.75
    Activations Density 0.008%

    No Known Activations