© 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. 40-GEMMASCOPE-2-RES-262K
    7. 34839
    Prev
    Next
    INDEX
    Explanations

    layout and rendering

    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_40_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
     triển
    0.39
     masti
    0.38
     SISO
    0.38
    ჯ
    0.37
    getActivity
    0.37
     stabilization
    0.36
     मश
    0.36
     Enrichment
    0.36
    фей
    0.35
     Singers
    0.35
    POSITIVE LOGITS
    getParent
    0.47
    addView
    0.45
    appendChild
    0.45
    repaint
    0.45
     father
    0.44
    father
    0.44
    getWidth
    0.44
     addSubview
    0.42
    父
    0.42
    removeAll
    0.42
    Activations Density 0.004%

    No Known Activations