© 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. 31079
    Prev
    Next
    INDEX
    Explanations

    company names and people

    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
    ヴ
    -0.81
    ϐ
    -0.79
     kró
    -0.78
    вали
    -0.76
     NIS
    -0.73
    ('');
    -0.72
    yeni
    -0.71
     terciopelo
    -0.71
     BufferedImage
    -0.71
    wä
    -0.71
    POSITIVE LOGITS
    حيان
    0.76
    cun
    0.76
    QUIZ
    0.67
    pj
    0.66
     īpa
    0.66
    aron
    0.66
     toilettes
    0.65
     raptor
    0.65
    大神
    0.65
     Cb
    0.64
    Activations Density 0.011%

    No Known Activations