© 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. 31-GEMMASCOPE-2-RES-262K
    7. 201801
    Prev
    Next
    INDEX
    Explanations

    hanging suspension bridges

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

    layoffs

    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_31_width_262k_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
    ▒
    0.48
    zeczytaj
    0.46
    holo
    0.46
    obsc
    0.46
    蘑
    0.45
    磴
    0.45
    
    0.45
    <0xC8>
    0.44
    本书
    0.43
    房間
    0.43
    POSITIVE LOGITS
    करा
    0.42
     சட்டமன்ற
    0.42
     patriotism
    0.40
     legislación
    0.40
    کٹ
    0.40
     bahwa
    0.40
     gentleman
    0.38
     citizenry
    0.38
     displeasure
    0.38
     आमदार
    0.38
    Activations Density 0.001%

    No Known Activations