© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6540
    Prev
    Next
    INDEX
    Explanations

    about blogging and marketing

    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
    Negative Logits
     можете
    0.43
    incere
    0.42
    ೬
    0.39
    ¦
    0.38
    Rain
    0.37
    <0x0E>
    0.37
     আপ
    0.37
    V
    0.36
    आपके
    0.36
    Pron
    0.36
    POSITIVE LOGITS
     hatch
    0.41
     hawk
    0.41
     lager
    0.39
    వులు
    0.38
     দায়
    0.37
    ikken
    0.37
     batches
    0.36
     LGA
    0.36
     spiral
    0.36
     tread
    0.36
    Activations Density 0.023%

    No Known Activations