© 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. 196933
    Prev
    Next
    INDEX
    Explanations

    combines scans browse

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

    .NET Core/.NET 6

    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
    ᕝ
    0.46
     بعمل
    0.42
     excepcional
    0.41
     জীববিজ্ঞান
    0.41
     بسيط
    0.41
    clad
    0.40
    竇
    0.40
     estre
    0.40
     উইল
    0.40
     그것
    0.39
    POSITIVE LOGITS
    曜日
    0.48
    Country
    0.45
    ch
    0.45
    交代
    0.44
    Commiss
    0.44
    ص
    0.43
    Writer
    0.43
    Authors
    0.43
     +'
    0.43
     scrivere
    0.42
    Activations Density 0.000%

    No Known Activations