© 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. 3121
    Prev
    Next
    INDEX
    Explanations

    questions starting with do or are

    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
    urel
    0.77
    occasione
    0.73
    +
    0.73
     aboard
    0.69
    ḳ
    0.65
     retrospect
    0.64
     brainchild
    0.63
     @
    0.61
    而成
    0.61
    神器
    0.58
    POSITIVE LOGITS
     does
    3.05
     Does
    2.97
    Does
    2.96
    does
    2.74
     do
    2.59
     did
    2.58
    Do
    2.57
    Are
    2.56
     Are
    2.55
     Do
    2.53
    Activations Density 0.655%

    No Known Activations