© 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. 39203
    Prev
    Next
    INDEX
    Explanations

    identifies list or index

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

    list items or file names

    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
    进攻
    0.45
     بھر
    0.41
    太过
    0.41
    梟
    0.40
    ല്‍
    0.40
     revenge
    0.40
     לת
    0.40
     प्रतिस्पर्
    0.40
     torment
    0.39
     Señor
    0.39
    POSITIVE LOGITS
     fileobj
    0.41
     regenv
    0.40
    ខ្ញ
    0.39
    рых
    0.39
     catalyzes
    0.38
    ；
    0.38
     ještě
    0.37
     GoObject
    0.37
     Indicates
    0.37
     ubiquitin
    0.37
    Activations Density 0.000%

    No Known Activations