© 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. 40-GEMMASCOPE-2-RES-65K
    7. 3896
    Prev
    Next
    INDEX
    Explanations

    html 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_40_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
    olyb
    0.24
    incontro
    0.24
    𐰑
    0.23
    ைகிறது
    0.23
     Macedonian
    0.23
    <unused993>
    0.23
    ങ്ങ്
    0.23
     Badajoz
    0.23
    𐰴
    0.23
     situ
    0.22
    POSITIVE LOGITS
          
    0.27
     terrorism
    0.25
    0.24
    сторінку
    0.24
     تاز
    0.24
    Bru
    0.24
    पुरा
    0.23
    CP
    0.23
    terrorism
    0.23
    Jackie
    0.23
    Activations Density 0.016%

    No Known Activations