© 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. 134555
    Prev
    Next
    INDEX
    Explanations

    organ music and medical terms

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

    introduces specific phrases

    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
    H
    0.61
    Neder
    0.49
    মানুষ
    0.48
    缭
    0.47
     Tư
    0.46
    ập
    0.46
    Neces
    0.46
    stwa
    0.46
    Cuenta
    0.45
    鋆
    0.45
    POSITIVE LOGITS
     polypes
    0.58
     underlie
    0.52
     endoscopic
    0.50
     polypeptides
    0.49
     exacerbate
    0.48
     denominators
    0.47
     worsens
    0.47
    мно
    0.47
     worsen
    0.46
     cliffs
    0.46
    Activations Density 0.000%

    No Known Activations