© 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. 105950
    Prev
    Next
    INDEX
    Explanations

    CA

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

    looking for

    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
     chân
    0.52
    ~\
    0.48
     từ
    0.46
    </sub>
    0.46
     servicing
    0.45
    
    0.45
    ất
    0.45
     serviced
    0.43
     anode
    0.43
     incineration
    0.43
    POSITIVE LOGITS
    म
    0.50
    et
    0.50
    വാ
    0.50
     ৯ম
    0.50
    reihe
    0.49
    N
    0.49
    Ნ
    0.48
    am
    0.48
     لوبه
    0.48
    šenje
    0.48
    Activations Density 0.000%

    No Known Activations