© 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. 249509
    Prev
    Next
    INDEX
    Explanations

    conducted or wrote

    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
     করুন
    0.50
     home
    0.48
     軽量
    0.48
     */}
    0.47
    க்கள்
    0.46
    即可
    0.45
     label
    0.45
     Retail
    0.44
    零售
    0.44
     Home
    0.44
    POSITIVE LOGITS
    Здравствуйте
    0.51
    ⵅ
    0.50
    NewUrl
    0.50
     Doremi
    0.49
    Hallo
    0.49
    𝚂
    0.46
    肐
    0.46
    Bokeh
    0.46
     ребенка
    0.45
    ⊡
    0.45
    Activations Density 0.000%

    No Known Activations