© 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. 214614
    Prev
    Next
    INDEX
    Explanations

    specific items in ordered lists

    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
    ▋
    0.38
     literalmente
    0.38
     गर्व
    0.38
     நன்றாக
    0.37
     искать
    0.37
    нием
    0.36
     sabía
    0.35
    加盟
    0.35
     అంశ
    0.35
    到处
    0.35
    POSITIVE LOGITS
     &&
    0.49
    use
    0.46
     odd
    0.42
     generating
    0.42
     Odd
    0.41
     generate
    0.40
     use
    0.40
     chev
    0.39
     sit
    0.39
     GENER
    0.39
    Activations Density 0.000%

    No Known Activations