© 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. 10281
    Prev
    Next
    INDEX
    Explanations

    consequential phrasing

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

    if clauses and subsequent actions

    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
     vienen
    0.41
     cuz
    0.38
    。
    0.37
    Assim
    0.37
     ultimi
    0.36
     tbh
    0.36
     visione
    0.35
     altres
    0.34
    0.34
     ہیں۔
    0.34
    POSITIVE LOGITS
    则
    0.60
    那就
    0.59
    則
    0.57
    它可以
    0.56
     thì
    0.56
    那么
    0.53
     then
    0.51
    then
    0.51
    那麼
    0.49
     则
    0.49
    Activations Density 0.071%

    No Known Activations