© 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-16K
    7. 8957
    Prev
    Next
    INDEX
    Explanations

    numbered list instructions

    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
     ഇന്ന്
    0.40
     sociology
    0.40
     lavage
    0.38
    -$
    0.38
     Subscribers
    0.38
    लेज
    0.37
     একটি
    0.37
     বলিয়াই
    0.36
    ยิ่ง
    0.36
     submarine
    0.36
    POSITIVE LOGITS
     அடை
    0.44
    neze
    0.40
    awatan
    0.40
    onha
    0.39
    thest
    0.38
     विच
    0.38
     Oso
    0.37
    ＞
    0.37
    illian
    0.36
    ności
    0.36
    Activations Density 0.003%

    No Known Activations