© 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. 99816
    Prev
    Next
    INDEX
    Explanations

    Reduced prompt engineering & training

    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
    @",
    0.41
    分け
    0.41
    ສົ
    0.41
     बीएससी
    0.40
     மூ
    0.39
     Боли
    0.39
    round
    0.39
    괄
    0.39
     Архиви
    0.39
     smer
    0.39
    POSITIVE LOGITS
     médiane
    0.52
    बिया
    0.47
     sapien
    0.46
     indexBuffer
    0.44
     taux
    0.44
     nowoczes
    0.44
    笕
    0.43
     ALF
    0.43
     woodwork
    0.43
     alum
    0.42
    Activations Density 0.006%

    No Known Activations