© 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. 8627
    Prev
    Next
    INDEX
    Explanations

    language markers

    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
     exclusivamente
    0.54
     decidido
    0.54
     atend
    0.54
    閡
    0.54
    കർ
    0.53
     poder
    0.52
     separado
    0.52
     disfruta
    0.52
     inilah
    0.52
     permitido
    0.51
    POSITIVE LOGITS
    ং
    0.58
     питань
    0.53
    ኛውም
    0.53
     awọn
    0.50
    муля
    0.50
                    
    0.49
     режими
    0.49
    जनबी
    0.49
    ுற
    0.48
    paw
    0.48
    Activations Density 0.191%

    No Known Activations