© 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. 31-GEMMASCOPE-2-RES-262K
    7. 55630
    Prev
    Next
    INDEX
    Explanations

    starting phrase or clause

    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_31_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
    Qualifications
    0.49
     jasa
    0.48
             
    0.45
     Eds
    0.45
     ailment
    0.44
    <unused1031>
    0.44
     ailments
    0.43
    Associate
    0.43
    issé
    0.43
    "=>
    0.42
    POSITIVE LOGITS
     soạn
    0.45
    ות
    0.44
     staring
    0.44
    دید
    0.43
    确认
    0.43
     STYLE
    0.42
     nào
    0.42
     популярных
    0.41
     plated
    0.40
    سى
    0.40
    Activations Density 0.001%

    No Known Activations