© 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. 49618
    Prev
    Next
    INDEX
    Explanations

    injury, financial, emotional

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

    cannot be employed, many uncontrolled

    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
     रिय
    0.44
     ትንሽ
    0.41
     ಫಲ
    0.41
    ServletException
    0.41
     나머
    0.40
     <%=
    0.40
    ્યુ
    0.39
     কষ্ট
    0.39
     আপনি
    0.39
     প্রকৃতির
    0.38
    POSITIVE LOGITS
    GUARD
    0.47
     GUARD
    0.41
    mph
    0.40
    ۔
    0.40
     trainings
    0.40
     Capital
    0.39
     amounting
    0.39
     دور
    0.38
    عداد
    0.38
     embe
    0.38
    Activations Density 0.000%

    No Known Activations