© 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-65K
    7. 6213
    Prev
    Next
    INDEX
    Explanations

    fall, recognize, shall

    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_65k_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
    RE
    0.48
    ０
    0.47
    sharp
    0.46
    歯
    0.46
    マー
    0.43
    １
    0.43
    ueroa
    0.43
    ಪು
    0.43
     गणपति
    0.43
    階段
    0.43
    POSITIVE LOGITS
     crow
    0.57
     wren
    0.50
     köl
    0.50
    erra
    0.48
     znam
    0.46
    ution
    0.44
     nue
    0.43
     correctes
    0.43
    MVCProject
    0.42
    Ớ
    0.42
    Activations Density 0.018%

    No Known Activations