© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2967
    Prev
    Next
    INDEX
    Explanations

    matlab code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    e
    2.07
    a
    1.99
    en
    1.62
     Column
    1.56
    的
    1.56
    er
    1.55
     Z
    1.54
    Column
    1.50
     Co
    1.50
    y
    1.49
    POSITIVE LOGITS
    듦
    1.76
    ції
    1.66
     srd
    1.64
     viven
    1.63
    psc
    1.62
     deportes
    1.61
    mmss
    1.59
     absolue
    1.59
     cnpj
    1.59
    olib
    1.58
    Activations Density 0.295%

    No Known Activations