© 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. 185838
    Prev
    Next
    INDEX
    Explanations

    phrases indicating steps or occurrences

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

    battling

    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
     которого
    0.55
     заве
    0.49
    ята
    0.47
    чатку
    0.45
    許可
    0.44
    কারী
    0.44
    эль
    0.43
    ৫
    0.43
    ￫
    0.43
    ુર
    0.42
    POSITIVE LOGITS
     noite
    0.50
     noche
    0.47
    newline
    0.46
     tienda
    0.45
    abelian
    0.43
    make
    0.43
    prav
    0.43
     ingred
    0.43
    Substituting
    0.42
     semaine
    0.42
    Activations Density 0.001%

    No Known Activations