© 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. 6993
    Prev
    Next
    INDEX
    Explanations

    typed custom classes

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

    words ending in based

    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
    ６
    0.38
    artigen
    0.37
     nessuna
    0.34
     ostatnich
    0.34
     Ouvrard
    0.34
    請問
    0.33
    ４
    0.33
    ۴
    0.33
     Neend
    0.32
     म्युच्युअल
    0.32
    POSITIVE LOGITS
     influencers
    0.34
     disruptions
    0.30
    u
    0.30
    re
    0.30
    라스
    0.29
    practices
    0.29
     practices
    0.29
     탄
    0.29
     ασ
    0.28
     פּ
    0.28
    Activations Density 0.533%

    No Known Activations