© 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. 75166
    Prev
    Next
    INDEX
    Explanations

    numbers, versions, and reviews

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

    and person breath

    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
    ๚
    0.61
     uguale
    0.54
     সংরক্ষণ
    0.52
     descricao
    0.52
    
    0.52
    
    0.51
    ார்கள்
    0.51
    エアコン
    0.49
    ੀ
    0.49
    ക്കാര
    0.48
    POSITIVE LOGITS
    oms
    0.59
    Tool
    0.49
    /
    0.48
    높
    0.43
    IC
    0.43
    Wheel
    0.42
     Ki
    0.42
     I
    0.42
    ICOS
    0.41
     Ic
    0.41
    Activations Density 0.002%

    No Known Activations