© 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. 200888
    Prev
    Next
    INDEX
    Explanations

    "I" followed by possessive, "boxes" followed by "there"

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

    code and descriptive text

    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
     unexpected
    0.49
     unforeseen
    0.49
     candidat
    0.45
     bookings
    0.42
    unexpected
    0.42
    ି
    0.41
     wrongdoing
    0.41
    
    0.40
    󠁬
    0.40
     booking
    0.40
    POSITIVE LOGITS
     سینٹی
    0.44
     মোটামুটি
    0.41
     அவருடைய
    0.39
     quanta
    0.39
     Meter
    0.38
     dunkel
    0.38
    Meter
    0.38
    四个
    0.37
    厘米
    0.37
     ಸುಮ
    0.37
    Activations Density 0.001%

    No Known Activations