© 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. 222347
    Prev
    Next
    INDEX
    Explanations

    technical syntax and structure

    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
    c
    0.48
    h
    0.47
    neck
    0.46
    č
    0.45
    layer
    0.42
    chill
    0.42
    grid
    0.41
    cap
    0.41
    ident
    0.40
    tan
    0.40
    POSITIVE LOGITS
    魅力
    0.49
     chooser
    0.44
     :+:
    0.43
    Transaksi
    0.42
     ITALY
    0.41
    货物
    0.41
    Escolh
    0.41
    Ⲏ
    0.41
     comboBox
    0.40
    㳡
    0.40
    Activations Density 0.009%

    No Known Activations