© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 83972
    Prev
    Next
    INDEX
    Explanations

    average weight

    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
     ثم
    0.42
     wild
    0.42
    期待
    0.42
     멋
    0.40
     homely
    0.38
     అక్కడ
    0.38
    EXPECT
    0.37
    place
    0.37
    ~/
    0.37
     disappointment
    0.36
    POSITIVE LOGITS
     snd
    0.44
     humanas
    0.43
    дык
    0.43
    㖩
    0.43
     Dewey
    0.42
     DeSantis
    0.42
    ıcı
    0.42
     prevision
    0.42
    Arc
    0.42
    込
    0.42
    Activations Density 0.005%

    No Known Activations