© 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. 141764
    Prev
    Next
    INDEX
    Explanations

    completing reconciliations art bar finally

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

    articulating what's next

    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
    f
    0.59
    $\
    0.58
    $$\
    0.52
    pbs
    0.52
    MAK
    0.49
    Ｆ
    0.49
    Stef
    0.49
    Shim
    0.49
    喜
    0.48
    យ៉
    0.47
    POSITIVE LOGITS
     bhfu
    0.47
     shaving
    0.44
    க்கப்பட்டுள்ளது
    0.44
     onClose
    0.44
     tbh
    0.43
     prostitute
    0.43
     chaining
    0.43
     translating
    0.43
     reconstructing
    0.43
     تھا
    0.42
    Activations Density 0.000%

    No Known Activations