© 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. 16-GEMMASCOPE-2-RES-262K
    7. 138665
    Prev
    Next
    INDEX
    Explanations

    amputation and its variants

    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_16_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
    し
    0.75
    ுகிறார்கள்
    0.63
    ૢ
    0.62
    according
    0.59
     multitud
    0.59
     अभी
    0.59
     σύμφωνα
    0.58
    υ
    0.58
    м
    0.58
     இருக்கிறது
    0.57
    POSITIVE LOGITS
     for
    0.64
     messo
    0.61
    <0x0D>
    0.58
    𝘰
    0.55
    问题的
    0.55
     amput
    0.54
    etak
    0.53
     enf
    0.52
     amputation
    0.52
    𝙖
    0.52
    Activations Density 0.001%

    No Known Activations