© 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
    2. Gemma-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 143
    Prev
    Next
    INDEX
    Explanations

    HTML links and Spanish

    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
    =
    1.85
    .=
    1.55
    (=
    1.52
     without
    1.52
    (“
    1.51
    here
    1.51
    accompanied
    1.50
    様子
    1.47
    adres
    1.45
    (
    1.43
    POSITIVE LOGITS
    rinsic
    2.78
     машин
    2.63
     общественных
    2.61
     транспорт
    2.56
     худо
    2.49
     кристал
    2.47
     торго
    2.46
     плат
    2.42
     граждан
    2.39
     муниципа
    2.39
    Activations Density 0.324%

    No Known Activations