© 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. 17031
    Prev
    Next
    INDEX
    Explanations

    oral, written, visual communication

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

    visual inspection, comparison, representation

    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
    ک
    0.54
    kts
    0.52
    多い
    0.51
    ೊಳ್ಳ
    0.50
    lamps
    0.50
    CTX
    0.49
    システム
    0.49
    ن
    0.48
     می
    0.48
    行う
    0.48
    POSITIVE LOGITS
     oral
    0.70
     orally
    0.64
    Oral
    0.62
     verbally
    0.61
     contraceptives
    0.59
    verbal
    0.57
     मौखिक
    0.57
     Oral
    0.56
     verbal
    0.56
    oral
    0.55
    Activations Density 0.108%

    No Known Activations