© 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. 860
    Prev
    Next
    INDEX
    Explanations

    reporting speech or actions

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

    pronoun followed by past tense verb

    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
    만
    0.35
     _.
    0.34
     Practically
    0.33
    됩니다
    0.32
     gotovo
    0.32
     layouts
    0.32
     implode
    0.32
    效
    0.32
     Helvetica
    0.32
    地形
    0.32
    POSITIVE LOGITS
     thanked
    0.54
     anunció
    0.48
     કહ્યું
    0.48
     informó
    0.46
     congratulated
    0.46
     apologized
    0.46
     withdrew
    0.45
     announced
    0.45
     said
    0.44
     apologised
    0.44
    Activations Density 0.089%

    No Known Activations