© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65076
    Prev
    Next
    INDEX
    Explanations

    school and schoolgirls

    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
    ınar
    -0.75
     Fondazione
    -0.69
     Cabrera
    -0.68
    IntOverflow
    -0.67
    opol
    -0.66
    ಾಗ
    -0.65
    ⠼
    -0.64
    成人
    -0.62
    UTIONS
    -0.62
     predict
    -0.61
    POSITIVE LOGITS
    andere
    1.09
    plier
    1.03
     school
    0.99
     الشرطة
    0.93
     kokona
    0.90
     School
    0.89
    School
    0.85
     darling
    0.84
     Netzwerk
    0.84
    school
    0.83
    Activations Density 0.007%

    No Known Activations