© 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. 251048
    Prev
    Next
    INDEX
    Explanations

    modification and suburban

    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
    VERY
    0.49
     cleft
    0.46
    OUR
    0.46
    שא
    0.46
    ⿹
    0.45
     horrors
    0.45
     어떻
    0.45
     ヘ
    0.45
    ROUTES
    0.45
    یع
    0.44
    POSITIVE LOGITS
     Modification
    0.45
    ashire
    0.41
     suburban
    0.39
    Modification
    0.39
     Saginaw
    0.39
     اثنين
    0.39
     modification
    0.37
     Suburban
    0.37
     обратиться
    0.37
     Karlsson
    0.37
    Activations Density 0.000%

    No Known Activations