© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8804
    Prev
    Next
    INDEX
    Explanations

    Huffington

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

    gemma

    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
    ड्रन
    0.41
     bande
    0.38
    값
    0.37
     VIE
    0.37
     corne
    0.36
    bandwidth
    0.36
    قق
    0.35
    count
    0.35
    ರಿಸ
    0.35
    emont
    0.35
    POSITIVE LOGITS
    ​—
    0.51
    ‑
    0.48
    ‐
    0.44
    -​
    0.42
     Huffington
    0.42
    ού
    0.41
    <0xE2>
    0.39
    Resizable
    0.38
     পূর্ব
    0.38
     ―
    0.38
    Activations Density 0.071%

    No Known Activations