© 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. 99893
    Prev
    Next
    INDEX
    Explanations

    technical acronyms and jargon

    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
    漀
    0.43
     volupt
    0.40
    𝓸
    0.36
    ░
    0.32
    োঁয়া
    0.32
    𝐚
    0.32
    ()<
    0.31
    ཟ
    0.31
    𓂃
    0.30
    身边
    0.30
    POSITIVE LOGITS
     ČR
    0.45
     BiH
    0.43
     SaaS
    0.43
     РФ
    0.42
     SMEs
    0.42
     Ư
    0.42
     FTIR
    0.41
     SSSR
    0.41
     SBOM
    0.40
     SCGS
    0.40
    Activations Density 0.568%

    No Known Activations