© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7331
    Prev
    Next
    INDEX
    Explanations

    equal rights. by attracting. bearded seals. Unilever consistently. licenses to transmit

    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
    ﻨ
    0.84
    ﺘ
    0.82
    ﺨ
    0.79
    reversed
    0.72
    བ་
    0.70
    ﺤ
    0.69
    ିକ
    0.68
    ﻤ
    0.68
    ﺖ
    0.66
    клады
    0.66
    POSITIVE LOGITS
     heat
    0.73
     dues
    0.72
     brilliant
    0.72
    ى
    0.72
     shutting
    0.71
     showed
    0.71
    اء
    0.71
     hunger
    0.71
    শু
    0.71
     visualizing
    0.71
    Activations Density 0.000%

    No Known Activations