© 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. 125485
    Prev
    Next
    INDEX
    Explanations

    diagnostic criteria, what matters

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

    planning lists and structures

    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
     Loy
    0.46
     کرے
    0.46
    Commit
    0.44
    い
    0.43
     SIP
    0.42
     προβ
    0.42
    ,
    0.42
    یه
    0.42
     producing
    0.42
    칭
    0.42
    POSITIVE LOGITS
     ಗ್ರಾಮ
    0.58
     腰
    0.50
     miljoen
    0.50
     muertos
    0.49
     fevereiro
    0.47
     ಹಲವಾರು
    0.46
     vuelo
    0.46
    শুর
    0.46
     tage
    0.46
     facteur
    0.45
    Activations Density 0.000%

    No Known Activations