© 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. 5412
    Prev
    Next
    INDEX
    Explanations

    file path delimiters

    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
     superstructure
    1.41
    的高度
    1.23
    ordial
    1.17
     equilibration
    1.17
    ørende
    1.15
    逅
    1.14
    ujj
    1.11
     shipbuilding
    1.09
     кури
    1.08
     interse
    1.08
    POSITIVE LOGITS
    팡
    1.89
     \%
    1.88
    ยนตร์
    1.81
    sni
    1.79
    ه
    1.76
     Breck
    1.75
    Webster
    1.74
    ETIME
    1.71
     STA
    1.70
     кажу
    1.70
    Activations Density 0.007%

    No Known Activations