© 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. 44348
    Prev
    Next
    INDEX
    Explanations

    press release

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

    list of programming terms

    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
     Marquette
    0.50
     Support
    0.48
     सपोर्ट
    0.46
     Figure
    0.45
     U
    0.44
     support
    0.44
    '
    0.43
     Restaurant
    0.42
     มุม
    0.42
     Marquis
    0.42
    POSITIVE LOGITS
    شتغل
    0.45
    改良
    0.40
    बरी
    0.37
    衔
    0.36
    년을
    0.35
    ಂದು
    0.35
    来自于
    0.35
    來自
    0.35
    myfaces
    0.34
    来自
    0.34
    Activations Density 0.000%

    No Known Activations