© 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. 5185
    Prev
    Next
    INDEX
    Explanations

    never felt experienced

    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
     bill
    1.29
     leak
    1.23
     outlet
    1.22
     tampering
    1.21
    deposit
    1.20
     scandalous
    1.17
    召
    1.17
     SLOT
    1.17
     role
    1.15
    kyt
    1.14
    POSITIVE LOGITS
    ̀u
    1.40
    ymal
    1.30
     εφαρ
    1.26
     UINavigation
    1.13
    実行
    1.11
    pedo
    1.11
     Galicia
    1.09
     navController
    1.06
     Demonstr
    1.06
     괜
    1.04
    Activations Density 0.022%

    No Known Activations