© 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. 12-GEMMASCOPE-2-RES-16K
    7. 16255
    Prev
    Next
    INDEX
    Explanations

    heading titles

    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_12_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
    ियों
    1.63
    ou
    1.61
    fungsi
    1.59
    ят
    1.59
    ɧ
    1.50
    ]")
    1.44
     enero
    1.42
    ен
    1.38
    ovala
    1.38
     ری
    1.36
    POSITIVE LOGITS
     agit
    1.65
    ه
    1.64
    нку
    1.63
    рова
    1.61
    うま
    1.58
     motiv
    1.57
    ند
    1.55
    くらいの
    1.55
     manipul
    1.54
     flops
    1.48
    Activations Density 0.009%

    No Known Activations