© 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. 244951
    Prev
    Next
    INDEX
    Explanations

    collocations following common words

    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
    льну
    0.55
    श्यक
    0.52
    яти
    0.52
     дошко
    0.51
     ప్రక
    0.50
    醣
    0.50
    一種
    0.49
    干部
    0.49
    铌
    0.49
     দাদার
    0.48
    POSITIVE LOGITS
     disables
    0.46
     colleague
    0.44
     bothers
    0.44
    ce
    0.44
    f
    0.43
     ferram
    0.43
     dares
    0.42
     evident
    0.42
     or
    0.42
    id
    0.41
    Activations Density 0.001%

    No Known Activations