© 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. 128037
    Prev
    Next
    INDEX
    Explanations

    specific clauses and explanations

    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
    0.56
     battery
    0.46
     views
    0.43
     product
    0.42
    者
    0.42
     wiggle
    0.41
    fords
    0.41
     batteries
    0.41
    كون
    0.40
     drum
    0.40
    POSITIVE LOGITS
    ά
    0.50
     apologised
    0.47
    Helvetica
    0.47
     angiel
    0.46
    ڈیا
    0.46
     কৃষ্ণ
    0.46
    <unused492>
    0.46
    .¹
    0.45
     צ
    0.45
    ostante
    0.45
    Activations Density 0.004%

    No Known Activations