© 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. 126372
    Prev
    Next
    INDEX
    Explanations

    Conversational interjections and specific origins

    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
    র
    0.54
    เบ
    0.47
     зона
    0.47
     dure
    0.44
     bassa
    0.43
    нить
    0.42
     मुख्यतः
    0.42
    όμε
    0.42
    ้ง
    0.41
     সরে
    0.41
    POSITIVE LOGITS
     indulged
    0.46
    연
    0.43
     leto
    0.42
     tịch
    0.42
     indulging
    0.42
    vana
    0.41
    睃
    0.40
     Frau
    0.40
    يس
    0.40
    禪
    0.40
    Activations Density 0.001%

    No Known Activations