© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 120600
    Prev
    Next
    INDEX
    Explanations

    listing and defining academic terms

    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
    loser
    0.43
    厦
    0.42
    Zm
    0.41
    rapy
    0.39
    ruik
    0.38
    dag
    0.38
    UISE
    0.37
    })+\
    0.37
     पद्धति
    0.37
     велико
    0.37
    POSITIVE LOGITS
     notation
    0.44
     ≥
    0.40
     geometric
    0.39
     >
    0.39
     notations
    0.38
     Br
    0.38
     genere
    0.38
     vector
    0.38
     Λ
    0.38
     Möbius
    0.37
    Activations Density 0.003%

    No Known Activations