© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7054
    Prev
    Next
    INDEX
    Explanations

    what other

    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_16k_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
    Bibliography
    0.39
     สา
    0.39
     प्राथमिक
    0.38
    </strong>
    0.37
     Research
    0.37
     Reception
    0.37
     স্বেচ্ছাসেব
    0.37
     آہستہ
    0.37
    ↵
    0.36
    POSITIVE LOGITS
     magari
    0.47
    вал
    0.47
     или
    0.46
    сто
    0.46
    <0xA1>
    0.45
     वगैरह
    0.45
    ном
    0.44
    不仅仅
    0.44
    ская
    0.43
    גל
    0.43
    Activations Density 0.287%

    No Known Activations