© 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. 241841
    Prev
    Next
    INDEX
    Explanations

    you followed by modal verbs

    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
    はない
    0.45
    溸
    0.44
    hibited
    0.43
    imd
    0.42
    at
    0.42
    _)
    0.42
    old
    0.41
    hut
    0.41
    ossi
    0.41
    native
    0.41
    POSITIVE LOGITS
     환
    0.46
    Clique
    0.44
     또한
    0.44
    cznie
    0.43
     setups
    0.43
     딸
    0.43
     المش
    0.43
     tots
    0.43
     전화
    0.43
     ور
    0.43
    Activations Density 0.001%

    No Known Activations