© 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. 28141
    Prev
    Next
    INDEX
    Explanations

    DOIs and citations

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

    journal DOIs

    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
     tranche
    0.44
    千
    0.40
     concatenated
    0.39
     candidate
    0.38
     multitude
    0.38
     myriad
    0.38
     कंग
    0.38
     زیرا
    0.37
     multidiscipl
    0.37
    integrated
    0.37
    POSITIVE LOGITS
     පමණ
    0.42
     Stay
    0.42
    辫
    0.41
    恻
    0.41
     событий
    0.40
    γεν
    0.40
    䔧
    0.40
    gas
    0.40
     Hike
    0.40
     Timm
    0.40
    Activations Density 0.007%

    No Known Activations