© 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. 139760
    Prev
    Next
    INDEX
    Explanations

    Thai and other languages

    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
    ].
    0.57
     மக்களின்
    0.50
     condomin
    0.48
     WITH
    0.48
     booked
    0.47
    ।
    0.46
     garnished
    0.46
    OU
    0.44
    <unused2066>
    0.44
     প্রস্তাব
    0.43
    POSITIVE LOGITS
    اب
    0.50
    력이
    0.50
    เช่น
    0.48
    ಲ್ಲ
    0.48
    క
    0.47
    counterx
    0.46
    ون
    0.46
    라
    0.45
    পি
    0.44
    న
    0.44
    Activations Density 0.000%

    No Known Activations