© 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. 84161
    Prev
    Next
    INDEX
    Explanations

    sensory perception, senses, bodily awareness

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

    sensory pleasure from nerve endings

    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
    obligation
    0.55
    ovenant
    0.53
    రుణ
    0.50
    
    0.50
    authorization
    0.49
    తు
    0.49
    谋
    0.49
    承诺
    0.49
    Obl
    0.48
    褙
    0.48
    POSITIVE LOGITS
     sensory
    1.44
     Sensory
    1.21
     sensorial
    1.13
     tactile
    1.07
     sensors
    1.03
     sensations
    0.95
     receptor
    0.95
     perception
    0.94
     perceiving
    0.93
     receptors
    0.92
    Activations Density 0.101%

    No Known Activations