© 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-65K
    7. 897
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_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
    shares
    0.66
    ahanga
    0.63
    systems
    0.61
    ylmethylsulfanyl
    0.60
    ו
    0.60
    sons
    0.59
    digits
    0.59
    sberg
    0.59
    sensors
    0.58
    diamond
    0.57
    POSITIVE LOGITS
    ύν
    0.73
    ый
    0.68
    κο
    0.66
     at
    0.61
     [
    0.59
     som
    0.57
    ε
    0.57
    υσ
    0.56
     a
    0.55
     |
    0.55
    Activations Density 0.000%

    No Known Activations