© 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. 166
    Prev
    Next
    INDEX
    Explanations

    verbs of speaking and asking

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

    verbs of saying or asking

    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
     dlg
    0.21
     sağlay
    0.20
    0.20
     oth
    0.20
     क
    0.20
     races
    0.20
     mg
    0.20
     οι
    0.19
     are
    0.19
     \
    0.19
    POSITIVE LOGITS
     jokingly
    0.28
     বলেছিল
    0.27
     voulait
    0.26
     કહ્યું
    0.26
     loudly
    0.26
     aloud
    0.25
    ٨
    0.25
    ed
    0.24
     বলেছিলেন
    0.24
     abiert
    0.23
    Activations Density 0.405%

    No Known Activations