© 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. 193379
    Prev
    Next
    INDEX
    Explanations

    describing qualities and actions

    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
     heterogeneity
    0.43
     decap
    0.41
     recovers
    0.39
     advers
    0.39
    湁
    0.39
    avourites
    0.38
    ạng
    0.38
     pernicious
    0.38
     versch
    0.38
     zust
    0.38
    POSITIVE LOGITS
    পাতি
    0.45
     tỏ
    0.39
    radi
    0.39
    ABLES
    0.37
     oczywiście
    0.37
    
    0.36
     dessous
    0.36
    veloc
    0.36
     pravil
    0.35
     Studios
    0.35
    Activations Density 0.002%

    No Known Activations