© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12269
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and negations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hooks
    0.40
     Esses
    0.37
     Hooks
    0.35
     Applies
    0.34
     pins
    0.34
     Assists
    0.34
     Assault
    0.33
     S
    0.33
     XIV
    0.33
    为主
    0.33
    POSITIVE LOGITS
     hacerlo
    0.50
     według
    0.44
     ঝুঁক
    0.42
    确实
    0.41
    殚
    0.40
     indeed
    0.39
    aurants
    0.39
     tijdens
    0.39
     pretože
    0.38
     farlo
    0.38
    Activations Density 0.012%

    No Known Activations