© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 738
    Prev
    Next
    INDEX
    Explanations

    Indian states and welfare funds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
     അവളെ
    1.13
     தீங்கு
    1.05
     magick
    1.04
     당신
    1.02
     Tamaño
    1.01
     Etsy
    1.00
     adaptador
    1.00
    𝄞
    0.99
     Mixtures
    0.98
     कपकेक
    0.96
    POSITIVE LOGITS
     Haryana
    1.48
     Rajya
    1.45
     Jammu
    1.41
     BJP
    1.40
     Jharkhand
    1.39
     Andhra
    1.38
     Telangana
    1.36
     Bharatiya
    1.36
     Punjab
    1.35
     Sindh
    1.34
    Activations Density 0.150%

    No Known Activations