© 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. 16-GEMMASCOPE-2-RES-262K
    7. 104854
    Prev
    Next
    INDEX
    Explanations

    marshmallows

    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_16_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
    indazol
    0.58
    𝓎
    0.53
    st
    0.53
     ک
    0.52
    uer
    0.52
     nó
    0.52
     سلس
    0.49
    σης
    0.49
     Lordships
    0.49
    号
    0.49
    POSITIVE LOGITS
    function
    0.59
    functions
    0.56
    াজিক
    0.53
    DICTION
    0.52
    TI
    0.50
    貘
    0.50
     function
    0.46
     people
    0.46
     intervention
    0.46
    ATING
    0.46
    Activations Density 0.000%

    No Known Activations