© 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. 64441
    Prev
    Next
    INDEX
    Explanations

    possessive determiners + nouns

    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
    istus
    -0.76
    AVAN
    -0.75
     Rb
    -0.75
    bois
    -0.73
     decidedly
    -0.72
     توضی
    -0.72
     AKP
    -0.71
     jotka
    -0.71
    particularly
    -0.71
    üh
    -0.70
    POSITIVE LOGITS
     numerous
    0.88
    consent
    0.87
     Leute
    0.84
    Gad
    0.82
    nend
    0.81
    umentar
    0.79
    ợt
    0.77
    Generated
    0.75
     silêncio
    0.74
     ©
    0.73
    Activations Density 0.011%

    No Known Activations