© 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. 31-GEMMASCOPE-2-RES-65K
    7. 8901
    Prev
    Next
    INDEX
    Explanations

    key nouns with definitions

    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_65k_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
     можно
    0.37
    ይን
    0.37
     ஏன்
    0.37
     Ats
    0.37
    <unused2189>
    0.36
     позволяют
    0.36
     अनिवार
    0.36
    を利用
    0.35
     ['(?
    0.35
     debía
    0.35
    POSITIVE LOGITS
     yaitu
    0.65
     consisting
    0.64
     which
    0.63
     iaitu
    0.59
     ossia
    0.59
    which
    0.58
     yakni
    0.55
     dvs
    0.55
     जोकि
    0.54
    ซึ่ง
    0.52
    Activations Density 0.368%

    No Known Activations