© 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. 184103
    Prev
    Next
    INDEX
    Explanations

    Russian and English nouns

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

    LEGOs and building blocks

    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
     Bled
    0.47
     Croatian
    0.46
     Disney
    0.46
     Hagen
    0.43
     Harga
    0.42
     Audubon
    0.42
     Bac
    0.42
    i
    0.42
     Box
    0.42
     Nau
    0.42
    POSITIVE LOGITS
    ifié
    0.55
    éments
    0.52
    ኚ
    0.52
     മാത്ര
    0.50
    servicetime
    0.50
     ഒന്നും
    0.49
    წიფ
    0.48
     appliquer
    0.48
    aturally
    0.47
    lestage
    0.47
    Activations Density 0.000%

    No Known Activations