© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 2005
    Prev
    Next
    INDEX
    Explanations

    const

    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_262k_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
    ’
    1.22
     metabolism
    1.20
    ’-
    1.09
    ’).
    1.09
     vortices
    1.07
     migrant
    1.06
     metastasis
    1.06
    的基础
    1.06
     extremity
    1.06
    汅
    1.06
    POSITIVE LOGITS
    c
    1.84
    s
    1.79
    o
    1.33
    по
    1.31
    pas
    1.31
    د
    1.30
    numbers
    1.25
    powers
    1.22
    prom
    1.20
    pare
    1.20
    Activations Density 0.003%

    No Known Activations