© 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. 1327
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and negation

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

    words like lot, after, require, do, without

    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
     lhe
    0.40
     P
    0.39
     subsection
    0.39
     AK
    0.39
     your
    0.38
     DIS
    0.37
     KAT
    0.37
     M
    0.37
    ٔ
    0.37
     Kat
    0.36
    POSITIVE LOGITS
     hacerlo
    0.95
     melakukannya
    0.89
     тако
    0.84
     farlo
    0.81
     ذلك
    0.67
     ones
    0.66
    ។
    0.64
    ።
    0.61
     그것
    0.61
    それは
    0.60
    Activations Density 0.529%

    No Known Activations