© 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. 1282
    Prev
    Next
    INDEX
    Explanations

    that followed by common words

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

    that introducing clauses

    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
    İL
    0.29
     删除
    0.28
    それが
    0.25
    ТА
    0.25
     żeby
    0.24
    ِينَ
    0.24
    न
    0.24
     '.</
    0.24
     Eğer
    0.24
     والن
    0.24
    POSITIVE LOGITS
     we
    0.44
     they
    0.38
     came
    0.35
     occurred
    0.34
     is
    0.33
     pertains
    0.32
     he
    0.31
     was
    0.31
     accompanies
    0.30
     precedes
    0.30
    Activations Density 0.431%

    No Known Activations