© 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. 117123
    Prev
    Next
    INDEX
    Explanations

    school levels and grades

    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
    że
    -0.77
    Locke
    -0.74
     sizable
    -0.74
    クラス
    -0.73
    ERVE
    -0.71
     prominent
    -0.71
    äischen
    -0.70
    LOCALE
    -0.69
    šní
    -0.69
    scan
    -0.69
    POSITIVE LOGITS
     secondary
    1.59
     primary
    1.44
     elementary
    1.40
    secondary
    1.26
     Primary
    1.25
     middle
    1.22
     Secondary
    1.19
     junior
    1.18
    Secondary
    1.16
    Primary
    1.14
    Activations Density 0.024%

    No Known Activations