© 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. 46986
    Prev
    Next
    INDEX
    Explanations

    Patrick Gary sight words

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

    testing boundaries

    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
    ເພ
    0.54
     её
    0.52
    _{(
    0.51
     તેની
    0.50
     τ
    0.50
    LEXPORT
    0.50
    
    0.49
    
    0.49
     તેના
    0.49
    _{*}$
    0.48
    POSITIVE LOGITS
     Patrick
    0.49
    p
    0.48
    sight
    0.47
    words
    0.45
    arach
    0.45
    at
    0.45
    sos
    0.45
    gary
    0.45
     Hm
    0.45
    Patrick
    0.44
    Activations Density 0.000%

    No Known Activations