© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 43334
    Prev
    Next
    INDEX
    Explanations

    zero or 0, version numbers, years

    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
    ।
    1.14
    스
    1.01
    ס
    0.99
    ש
    0.98
    י
    0.89
     ।
    0.87
    ר
    0.86
     divulg
    0.85
    ק
    0.82
    다
    0.81
    POSITIVE LOGITS
    izing
    0.88
    ized
    0.85
    них
    0.80
    们
    0.71
    了一个
    0.71
     و
    0.70
    ية
    0.70
    ças
    0.69
    يل
    0.69
    ze
    0.68
    Activations Density 0.000%

    No Known Activations