© 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. 51240
    Prev
    Next
    INDEX
    Explanations

    city, districts, titles, potentially

    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
     pulled
    0.50
     entertained
    0.47
    ↵↵
    0.44
    úscula
    0.44
     پیپلز
    0.43
     rested
    0.43
     permintaan
    0.43
    ،
    0.42
    pul
    0.42
     ه
    0.41
    POSITIVE LOGITS
    њу
    0.45
     أرض
    0.43
    profitLoss
    0.42
     conduction
    0.41
    轼
    0.41
     ActionResult
    0.40
     Winery
    0.40
    ми
    0.39
     Commerce
    0.39
     પોલી
    0.39
    Activations Density 0.010%

    No Known Activations