© 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. 28188
    Prev
    Next
    INDEX
    Explanations

    special characters and markers

    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
     either
    0.40
     દેશ
    0.38
     \
    0.37
     தென்
    0.37
     old
    0.36
     വലിയ
    0.36
     '
    0.35
     televis
    0.35
     chinese
    0.35
     tecnici
    0.35
    POSITIVE LOGITS
    两人
    0.45
    akor
    0.41
    ⊆
    0.40
    ('/:
    0.40
    営業時間
    0.40
    ₁(
    0.39
    兩人
    0.39
    ဟုတ်
    0.39
    그리고
    0.38
    嬅
    0.38
    Activations Density 0.001%

    No Known Activations