© 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. 75229
    Prev
    Next
    INDEX
    Explanations

    plans, assignments, events, medication

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

    models being translated

    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
    棧
    0.47
    ীষ
    0.45
     συγκ
    0.44
    栈
    0.43
     तस्वी
    0.42
    瀘
    0.42
    ত্ত্ব
    0.41
    idata
    0.41
    匯
    0.40
    OfInterest
    0.40
    POSITIVE LOGITS
    这么多
    0.50
     siendo
    0.47
     niemals
    0.47
     gleichzeitig
    0.46
     beş
    0.46
     estar
    0.45
     being
    0.45
     estando
    0.44
     jamás
    0.42
     periods
    0.42
    Activations Density 0.002%

    No Known Activations