© 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. 40-GEMMASCOPE-2-RES-262K
    7. 212404
    Prev
    Next
    INDEX
    Explanations

    understanding, measures, excel

    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
    FontSize
    0.42
     mostly
    0.38
     DIY
    0.38
    દા
    0.37
    ह
    0.37
     knobs
    0.36
     제조
    0.35
    橋
    0.35
     containers
    0.35
    thickness
    0.35
    POSITIVE LOGITS
     সেনাবাহ
    0.46
    獰
    0.45
     требуют
    0.44
    回事
    0.43
    international
    0.42
     சர்வதேச
    0.41
    England
    0.41
     internacionales
    0.41
     internationally
    0.39
     requieren
    0.39
    Activations Density 0.004%

    No Known Activations