© 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-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7222
    Prev
    Next
    INDEX
    Explanations

    sensory sensation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Context
    0.37
     يحت
    0.36
    úč
    0.36
    fet
    0.36
    coma
    0.36
     আলোকিত
    0.35
     elabor
    0.35
    ቼ
    0.35
     Yosh
    0.35
     চলেছে
    0.35
    POSITIVE LOGITS
     sensory
    1.27
     sensation
    1.25
     sensations
    1.23
     Sensory
    1.16
     numbness
    1.12
     sensação
    1.05
     sensibilidad
    1.03
     sensación
    1.01
     sensorial
    1.01
    Sens
    0.98
    Activations Density 0.209%

    No Known Activations