© 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. 132840
    Prev
    Next
    INDEX
    Explanations

    Milton and Hilton surnames

    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
     वातावरण
    0.38
     мг
    0.38
     यु
    0.38
    ం
    0.37
     आण
    0.37
    歎
    0.36
     어느
    0.36
     cien
    0.36
     ఒ
    0.35
     iniziato
    0.35
    POSITIVE LOGITS
     Hamburg
    0.44
     Milton
    0.43
     Paradise
    0.43
    setLocation
    0.41
     gyroscope
    0.40
     Keynes
    0.39
    鐐
    0.38
     হাসিনা
    0.37
     Walmart
    0.37
     vom
    0.37
    Activations Density 0.001%

    No Known Activations