© 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. 143801
    Prev
    Next
    INDEX
    Explanations

    numbers and statistics

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

    functional testing, human cognitive, earlier evidence

    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
    ₂,
    0.50
    ²,
    0.45
     इलेक्ट्रॉनिक
    0.45
     తర్వాత
    0.45
    氇
    0.45
    ⌛
    0.44
     பல்கலைக்கழக
    0.44
    Borrow
    0.44
    ፣
    0.43
    ₃
    0.43
    POSITIVE LOGITS
     abit
    0.51
     devenir
    0.46
     ajust
    0.46
     enem
    0.45
     enorm
    0.44
     lessen
    0.44
     renounce
    0.44
     changements
    0.43
     addTo
    0.43
     mniej
    0.43
    Activations Density 0.003%

    No Known Activations