© 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. 222088
    Prev
    Next
    INDEX
    Explanations

    Initialize Fibonacci numbers

    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
    /**
    0.50
    ítő
    0.44
    ('
    0.42
    getenv
    0.40
    fromj
    0.38
    nn
    0.38
    ▓
    0.37
    জর
    0.37
    SD
    0.37
    াকর্ম
    0.37
    POSITIVE LOGITS
     gate
    0.46
     Vaish
    0.43
     beat
    0.41
     ذات
    0.41
     عبارت
    0.41
     터
    0.41
     ابتدا
    0.41
     letzt
    0.41
     మొద
    0.40
    泍
    0.40
    Activations Density 0.000%

    No Known Activations