© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 164884
    Prev
    Next
    INDEX
    Explanations

    computing, language, or analysis

    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
    풀
    0.39
     imposible
    0.39
     फाउंडेशन
    0.38
     profesión
    0.37
     trae
    0.37
     corz
    0.37
    딕
    0.37
    欹
    0.36
     asynchronous
    0.36
     parado
    0.36
    POSITIVE LOGITS
    Ȼ
    0.38
     valore
    0.38
    IFIER
    0.38
     നിര്‍
    0.37
     tomu
    0.37
     LNG
    0.35
    crumbs
    0.35
    unker
    0.35
     Holder
    0.35
    }:$
    0.34
    Activations Density 0.000%

    No Known Activations