© 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. 17349
    Prev
    Next
    INDEX
    Explanations

    escape

    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
     основные
    0.45
     aliments
    0.41
    ת
    0.41
    ῆς
    0.40
     か
    0.40
     அறிய
    0.38
    有無
    0.38
    ड़ा
    0.37
    อ่ะ
    0.37
    ਮ
    0.37
    POSITIVE LOGITS
     Archivlink
    0.43
     रफ्तार
    0.38
     महज
    0.37
     삼각형
    0.36
     extré
    0.35
     அவன்
    0.35
     plötzlich
    0.35
     tehd
    0.34
     evaporate
    0.34
    শি
    0.34
    Activations Density 0.003%

    No Known Activations