© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 168820
    Prev
    Next
    INDEX
    Explanations

    all *allow*

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ولي
    0.40
    icen
    0.37
    Dollars
    0.36
    ԝ
    0.36
    Qualifier
    0.35
    Builder
    0.35
    quasi
    0.35
    发生
    0.34
    Hep
    0.34
     :
    0.34
    POSITIVE LOGITS
     friendship
    0.46
     Fontainebleau
    0.45
     Friendship
    0.42
    न्यूयॉर्क
    0.41
     friendships
    0.41
     Bibliothèque
    0.41
     επικ
    0.40
     biblioteca
    0.40
     Dorchester
    0.40
     northeast
    0.39
    Activations Density 0.000%

    No Known Activations