© 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. 9139
    Prev
    Next
    INDEX
    Explanations

    size of

    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
     Imm
    0.62
     высокого
    0.62
     Internacional
    0.61
     TED
    0.61
     wysok
    0.61
     UVA
    0.61
     kleuren
    0.61
    ﾂ
    0.60
     શુભેચ્છ
    0.59
    Grav
    0.59
    POSITIVE LOGITS
    尺寸
    0.71
    Size
    0.70
     reduction
    0.68
     getSize
    0.67
    SizeMode
    0.66
    ඍ
    0.65
    Sizes
    0.61
     reducido
    0.60
     Size
    0.59
     SIZE
    0.59
    Activations Density 0.153%

    No Known Activations