© 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. 112175
    Prev
    Next
    INDEX
    Explanations

    locations and non-English characters

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

    ambiguity

    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
     sebagaimana
    0.50
     perte
    0.43
    揄
    0.42
     nuo
    0.42
     intang
    0.41
     nilai
    0.40
    пки
    0.40
     нуля
    0.40
     invisibility
    0.40
    ᒋ
    0.40
    POSITIVE LOGITS
    atch
    0.43
    locations
    0.42
    UTE
    0.42
    commerce
    0.42
    স্পষ্ট
    0.42
    Locations
    0.39
     இடத்தில்
    0.39
    辞典
    0.39
     नाल
    0.39
    ็ม
    0.38
    Activations Density 0.002%

    No Known Activations