© 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. 6004
    Prev
    Next
    INDEX
    Explanations

    specific actions or improvements

    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
     to
    0.41
     taco
    0.39
     pergunt
    0.36
     analyte
    0.35
     mengatakan
    0.35
     hôm
    0.35
     diminta
    0.35
     「
    0.34
     says
    0.34
     seas
    0.34
    POSITIVE LOGITS
    Cher
    0.37
    ovariant
    0.36
     Hauptstadt
    0.36
     മികച്ച
    0.35
    और
    0.34
    Traité
    0.34
    aksha
    0.34
    Improved
    0.33
    ඍ
    0.33
    The
    0.33
    Activations Density 0.180%

    No Known Activations