© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 691
    Prev
    Next
    INDEX
    Explanations

    model code blocks

    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
    erina
    0.46
    auf
    0.41
    ()>
    0.39
     $>
    0.39
     入り
    0.38
     вход
    0.38
    harris
    0.38
     બંધ
    0.37
    ('#
    0.37
    ໃຫ້
    0.37
    POSITIVE LOGITS
    ```
    0.48
     certainly
    0.47
    Certainly
    0.46
     yes
    0.46
     Yes
    0.45
     Certainly
    0.45
     Below
    0.44
    Yes
    0.43
    Below
    0.43
     kyll
    0.41
    Activations Density 0.021%

    No Known Activations