© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 124524
    Prev
    Next
    INDEX
    Explanations

    comfort, comedy, developed, five, need, like

    np_acts-logits-general · gemini-2.5-flash-lite

    safe sex or risk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    揚
    0.53
     Toy
    0.49
    も見
    0.44
    も
    0.43
    Toy
    0.42
     Till
    0.42
     Toys
    0.42
     Eller
    0.41
    Toys
    0.41
     Shade
    0.41
    POSITIVE LOGITS
     imposible
    0.58
     novembro
    0.56
     finalmente
    0.54
    ).'
    0.52
     автомобиль
    0.52
     excellente
    0.52
     플
    0.51
     excelente
    0.50
     архитек
    0.50
     ग्लो
    0.50
    Activations Density 0.001%

    No Known Activations