© 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-262K
    7. 169401
    Prev
    Next
    INDEX
    Explanations

    man fire, alternating movement, Request permission

    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_262k_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
     Army
    0.59
    Army
    0.57
    軍
    0.54
     battlefield
    0.53
     ejército
    0.51
     regiments
    0.50
     infantry
    0.48
     army
    0.47
     Infantry
    0.46
     軍
    0.45
    POSITIVE LOGITS
    Rotate
    0.44
     પેટ
    0.44
    Rotation
    0.43
     Rotation
    0.42
     Rotate
    0.41
    旋转
    0.41
     সম্পত্তি
    0.41
     Caravan
    0.40
     kaldığımız
    0.40
    美容
    0.40
    Activations Density 0.006%

    No Known Activations