© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5889
    Prev
    Next
    INDEX
    Explanations

    process is complex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    下記の
    0.72
    :.
    0.72
     séjour
    0.69
    :
    0.69
     Major
    0.67
    see
    0.60
    oker
    0.58
     lain
    0.57
    .
    0.57
    引き続き
    0.53
    POSITIVE LOGITS
     entails
    3.57
    というのは
    3.48
     betekent
    3.47
     complicates
    3.46
     vuol
    3.44
     necessitates
    3.34
     implies
    3.28
     isn
    3.28
     significa
    3.28
     eliminates
    3.22
    Activations Density 0.980%

    No Known Activations