© 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. 3577
    Prev
    Next
    INDEX
    Explanations

    introducing stated conditions

    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
    тием
    1.26
    れの
    1.25
    とにかく
    1.19
    、“
    1.17
    ,@
    1.09
    、「
    1.07
    }}{{
    1.06
     ©
    1.06
     rapporte
    1.03
    et
    1.03
    POSITIVE LOGITS
    iqi
    1.30
     perturbative
    1.25
     océ
    1.23
     ParkingLot
    1.22
     Novos
    1.17
    ingar
    1.14
    ⌔
    1.12
     članak
    1.11
     Parth
    1.11
     nirv
    1.10
    Activations Density 0.111%

    No Known Activations