© 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. 77866
    Prev
    Next
    INDEX
    Explanations

    angel investor

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    chenen
    -0.75
     Projeto
    -0.74
    weixin
    -0.74
     Kirch
    -0.73
    PROJECT
    -0.71
    spun
    -0.70
     Equipe
    -0.70
     detainees
    -0.69
    olia
    -0.69
    पु
    -0.68
    POSITIVE LOGITS
     angel
    2.69
     angels
    2.23
     Angel
    2.11
    angel
    2.05
     Angels
    1.98
    Angel
    1.86
    Angels
    1.70
    ANGEL
    1.65
     ANGEL
    1.52
    angels
    1.45
    Activations Density 0.022%

    No Known Activations