© 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. 91811
    Prev
    Next
    INDEX
    Explanations

    clarity and adoption

    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
     )))
    0.48
    anin
    0.47
    -(\
    0.47
    ₁,
    0.46
    ὠ
    0.46
     недели
    0.45
     प्रणाली
    0.44
     সমষ্টি
    0.44
    ůli
    0.44
    -,
    0.43
    POSITIVE LOGITS
    lights
    0.50
     Maladies
    0.42
     armchair
    0.42
     Kunststoff
    0.41
     familiar
    0.41
    ירים
    0.41
     Jeddah
    0.41
    リーブ
    0.40
    يسي
    0.40
     sticky
    0.40
    Activations Density 0.011%

    No Known Activations