© 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. 53-GEMMASCOPE-2-RES-262K
    7. 81852
    Prev
    Next
    INDEX
    Explanations

    training pipelines and ai programs

    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_53_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
    艐
    0.42
     Российской
    0.40
    硃
    0.39
     нарко
    0.38
    聸
    0.38
     लोकार्
    0.38
    🌹
    0.38
    鄀
    0.38
    垲
    0.38
    ⎤
    0.37
    POSITIVE LOGITS
     T
    0.40
     lives
    0.39
     and
    0.39
     programs
    0.38
     Tide
    0.38
    m
    0.38
    шна
    0.38
    ai
    0.38
     X
    0.38
     adjustments
    0.38
    Activations Density 0.003%

    No Known Activations