© 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. 31-GEMMASCOPE-2-RES-262K
    7. 101204
    Prev
    Next
    INDEX
    Explanations

    explains Thunderbird networks filename models color

    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_31_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
    ੀ
    0.48
    ཥ
    0.48
    ید
    0.47
    INAL
    0.46
    जैसा
    0.46
    א
    0.45
    प्र
    0.45
    ក្រោម
    0.45
    を作
    0.45
    副
    0.44
    POSITIVE LOGITS
    łaszcza
    0.48
     confuses
    0.44
     críticos
    0.40
     例如
    0.40
     Cham
    0.39
     удержи
    0.38
     Flash
    0.38
     *
    0.38
    otas
    0.38
     Linux
    0.37
    Activations Density 0.004%

    No Known Activations