© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 212428
    Prev
    Next
    INDEX
    Explanations

    doctor or engineer specific roles

    np_acts-logits-general · gemini-2.5-flash-lite

    legal writing redundancy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Antrieb
    0.57
    ژ
    0.54
     visant
    0.53
     nessuna
    0.50
    針對
    0.48
    ل
    0.48
     ඔවුන්
    0.47
     peux
    0.47
     Selon
    0.46
     nessun
    0.46
    POSITIVE LOGITS
    JEE
    0.47
     spar
    0.47
    诒
    0.45
    ua
    0.45
    yser
    0.45
    jee
    0.44
     kites
    0.44
    jy
    0.44
     leaves
    0.43
     vestidos
    0.43
    Activations Density 0.000%

    No Known Activations