© 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. 227911
    Prev
    Next
    INDEX
    Explanations

    -ing suffix followed by a name

    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
     embodied
    0.43
     Điều
    0.43
     সমাপ্ত
    0.43
    versive
    0.42
    τη
    0.41
     Kd
    0.41
     {(
    0.41
     Aire
    0.41
    šk
    0.40
    h
    0.40
    POSITIVE LOGITS
     знают
    0.46
     lavorare
    0.45
     தெரிய
    0.43
     communicate
    0.43
     работал
    0.43
    旁边
    0.42
    ๓
    0.42
    ээ
    0.42
     entice
    0.41
    诖
    0.41
    Activations Density 0.001%

    No Known Activations