© 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. 89773
    Prev
    Next
    INDEX
    Explanations

    bull riding and tithing

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

    verbs followed by prepositions or specific words

    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
    তনা
    0.50
    迪士尼
    0.46
    姣
    0.46
     zvyš
    0.46
     aumentar
    0.45
    ة
    0.44
     tasas
    0.44
    ണ്
    0.44
    专项
    0.43
    毓
    0.43
    POSITIVE LOGITS
    ClassObject
    0.55
     presidents
    0.47
     electing
    0.46
     whence
    0.46
    ni
    0.45
    stressed
    0.45
     elected
    0.45
     objecting
    0.45
     oncoming
    0.44
    controller
    0.44
    Activations Density 0.003%

    No Known Activations