© 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. 31-GEMMASCOPE-2-RES-262K
    7. 101332
    Prev
    Next
    INDEX
    Explanations

    specific actions and states

    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_31_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
    рано
    0.45
    ко
    0.44
    ی
    0.43
     boleh
    0.42
     wdir
    0.42
     eaten
    0.42
    ানে
    0.41
     konsumen
    0.40
     capazes
    0.40
    лый
    0.40
    POSITIVE LOGITS
    oup
    0.47
     പിന്നീട്
    0.45
    Pattern
    0.45
    nson
    0.45
    cord
    0.44
    iare
    0.44
    itherto
    0.44
     ଚ
    0.43
    instance
    0.43
    عام
    0.43
    Activations Density 0.004%

    No Known Activations