© 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-262K
    7. 202470
    Prev
    Next
    INDEX
    Explanations

    prestigious, parameters, visualizing

    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_262k_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
     mosquitoes
    0.46
    ”(
    0.45
    ":"
    0.44
    Ī
    0.43
     ants
    0.43
     erlaubt
    0.43
    miner
    0.42
    ೪
    0.40
     equipping
    0.40
     permitir
    0.40
    POSITIVE LOGITS
    стая
    0.51
    特殊的
    0.47
    пети
    0.44
     célébr
    0.43
    优雅
    0.43
     красивые
    0.43
    Cake
    0.42
     hưởng
    0.42
     श्रद्धांजलि
    0.41
    简单的
    0.40
    Activations Density 0.006%

    No Known Activations