© 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. 15-GEMMASCOPE-2-RES-16K
    7. 1469
    Prev
    Next
    INDEX
    Explanations

    change and evolve

    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_15_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
    afd
    1.64
    etapkan
    1.59
     maintenir
    1.56
     پائی
    1.56
    ziehung
    1.52
    applique
    1.52
    versions
    1.51
    癜
    1.51
    ference
    1.50
    isière
    1.49
    POSITIVE LOGITS
    Alam
    0.95
    رجال
    0.93
    BATCH
    0.93
    ∑</
    0.90
    Skeleton
    0.90
     нала
    0.89
    Golden
    0.88
    Das
    0.88
    Networks
    0.86
     ανθ
    0.86
    Activations Density 0.409%

    No Known Activations