© 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. 146330
    Prev
    Next
    INDEX
    Explanations

    posted in categories

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

    language and moral frameworks

    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
    اگر
    0.51
    ினாலும்
    0.49
    Henri
    0.47
    Nathan
    0.46
    wc
    0.45
     حق
    0.45
    ت
    0.45
    ी
    0.44
    不仅
    0.43
    不僅
    0.43
    POSITIVE LOGITS
     rhetorical
    0.54
    群体
    0.52
    廉
    0.50
     bew
    0.49
    лім
    0.47
    pathi
    0.46
     cheers
    0.45
    мым
    0.45
    쿰
    0.45
     zapro
    0.44
    Activations Density 0.001%

    No Known Activations