© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 118965
    Prev
    Next
    INDEX
    Explanations

    exciton dissociation, binding, separation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    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
     tinkering
    0.63
     structures
    0.61
     diversifying
    0.60
    h
    0.60
    ალური
    0.59
     granular
    0.59
     partnering
    0.59
    中です
    0.59
     calm
    0.58
     сама
    0.58
    POSITIVE LOGITS
    ib
    0.70
     Permits
    0.67
    ip
    0.62
     الذي
    0.61
     أك
    0.61
    0
    0.59
    ij
    0.58
    bij
    0.58
    ين
    0.57
    ütt
    0.55
    Activations Density 0.001%

    No Known Activations