© 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. 680
    Prev
    Next
    INDEX
    Explanations

    descriptive state

    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
     माना
    0.37
    认为
    0.30
     wanneer
    0.30
     значений
    0.30
    рад
    0.29
    ѕ
    0.29
     ग्रंथ
    0.29
    人们
    0.29
    衍
    0.29
     توانید
    0.29
    POSITIVE LOGITS
     located
    0.48
     stored
    0.41
     unlabeled
    0.41
     labeled
    0.41
     hardcover
    0.41
     copyrighted
    0.40
     backlit
    0.40
    located
    0.40
     behaving
    0.39
     protected
    0.39
    Activations Density 0.036%

    No Known Activations