© 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. 4344
    Prev
    Next
    INDEX
    Explanations

    breakdown of options

    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
    rist
    0.45
     niewiel
    0.45
     preuves
    0.41
    ූ
    0.41
     lille
    0.41
     lancement
    0.40
     blandit
    0.40
    первых
    0.39
     congenial
    0.39
    Гу
    0.39
    POSITIVE LOGITS
     table
    0.71
    各
    0.68
    それぞれの
    0.65
     Table
    0.65
    Table
    0.63
    分别
    0.63
     各
    0.63
     respective
    0.61
     Tabelle
    0.59
    table
    0.58
    Activations Density 1.043%

    No Known Activations