© 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. 81233
    Prev
    Next
    INDEX
    Explanations

    plenty of

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

    plenty of

    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
     değişik
    0.60
     их
    0.59
     påver
    0.59
     ή
    0.57
     onların
    0.55
     arası
    0.55
    c
    0.55
     incredible
    0.53
     oneness
    0.52
     AMAZING
    0.52
    POSITIVE LOGITS
     plenty
    0.77
     suffisante
    0.75
    Plenty
    0.74
    넉
    0.73
     Plenty
    0.73
     충분
    0.73
     достат
    0.72
     sufficient
    0.71
     Sufficient
    0.71
     पर्याप्त
    0.70
    Activations Density 0.113%

    No Known Activations