© 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. 221921
    Prev
    Next
    INDEX
    Explanations

    pronoun verb or noun following punctuation

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

    adverb before 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
    定时
    0.50
    其他
    0.47
    WORK
    0.43
     activar
    0.42
    던
    0.41
    amatan
    0.41
    stances
    0.40
    学生
    0.40
     습
    0.40
    OTHER
    0.40
    POSITIVE LOGITS
     völlig
    0.56
     überzeugt
    0.52
     région
    0.51
     Straßen
    0.51
     geht
    0.48
     unang
    0.48
     äl
    0.47
     bislang
    0.47
     häufig
    0.47
     Świę
    0.46
    Activations Density 0.000%

    No Known Activations