© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10492
    Prev
    Next
    INDEX
    Explanations

    common phrases and beginnings

    np_acts-logits-general · gemini-2.5-flash-lite

    word combinations and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ArrayRef
    0.34
    উদ্দিন
    0.33
     continúa
    0.32
     androidx
    0.32
     মেডিকেল
    0.32
     Obituary
    0.32
    </h3>
    0.31
    ).(
    0.31
     الموجود
    0.31
     หลังจาก
    0.31
    POSITIVE LOGITS
    ifies
    0.41
     it
    0.37
    ogeneities
    0.35
    oubtedly
    0.33
     tendencies
    0.33
     assez
    0.32
    特に
    0.32
     danno
    0.32
    ≖
    0.32
    ian
    0.32
    Activations Density 0.723%

    No Known Activations