© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12290
    Prev
    Next
    INDEX
    Explanations

    programming languages and technical 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
    》《
    0.34
    ަތ
    0.32
    ῦ
    0.31
    }$}
    0.31
     isotopes
    0.31
    ˆ
    0.31
     वनडे
    0.30
    KA
    0.29
     annealed
    0.29
    舷
    0.29
    POSITIVE LOGITS
    лександр
    0.39
     USS
    0.39
     titular
    0.35
     Ubuy
    0.35
    judul
    0.33
     chiế
    0.32
     Thos
    0.32
     فه
    0.32
     GDPPC
    0.32
    nemis
    0.32
    Activations Density 0.075%

    No Known Activations