© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15171
    Prev
    Next
    INDEX
    Explanations

    itinerary planning or structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     camb
    0.46
     scroll
    0.45
    ELD
    0.43
    <strong>
    0.42
    CA
    0.39
     especialmente
    0.39
     crem
    0.38
     plant
    0.38
     noved
    0.38
     desplaz
    0.37
    POSITIVE LOGITS
    𒃶
    0.50
    ૬
    0.49
     በጥ
    0.47
    toh
    0.47
    悹
    0.47
    dSample
    0.46
     ছয়
    0.45
     ডিগ্র
    0.45
    ຮູ້
    0.45
     ถ้า
    0.45
    Activations Density 0.003%

    No Known Activations