© 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. 57399
    Prev
    Next
    INDEX
    Explanations

    approximate financial amounts

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

    "all ears" idiom with AI alternatives

    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
    новні
    0.50
     করছি
    0.49
    arette
    0.46
    संधान
    0.45
    کیل
    0.43
    FontStyle
    0.43
    भंगा
    0.42
    𝓑
    0.41
    getVisibility
    0.41
    填写
    0.41
    POSITIVE LOGITS
     fudai
    0.53
    睇
    0.48
     zuen
    0.48
    両
    0.48
     ≈
    0.48
    ≈
    0.47
    メ
    0.47
     aprox
    0.46
    及び
    0.45
     japon
    0.45
    Activations Density 0.000%

    No Known Activations