© 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. 55225
    Prev
    Next
    INDEX
    Explanations

    to a, to 2

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

    commitment or distance

    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
     établ
    0.50
     Mehta
    0.45
    t
    0.44
     trội
    0.43
     établissements
    0.42
    établ
    0.42
     Zachary
    0.41
    s
    0.41
     Identifier
    0.41
     hxg
    0.41
    POSITIVE LOGITS
     يا
    0.46
    
    0.46
    πος
    0.45
    ParamNum
    0.44
    嗉
    0.43
     مزید
    0.43
     messed
    0.43
     probabilidad
    0.42
     ornamented
    0.42
     shameful
    0.42
    Activations Density 0.000%

    No Known Activations