© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5857
    Prev
    Next
    INDEX
    Explanations

    will then print

    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
    รง
    1.20
    urban
    1.18
    Uber
    1.15
    éor
    1.14
     axiom
    1.13
    퓸
    1.10
    OMB
    1.10
    缪
    1.09
    regulars
    1.08
    プション
    1.08
    POSITIVE LOGITS
    etics
    1.78
    ระดับ
    1.64
    칠
    1.59
    ỏng
    1.59
    ETE
    1.58
     juega
    1.54
     Grades
    1.50
    แข่ง
    1.50
     شئ
    1.48
    ETS
    1.48
    Activations Density 0.036%

    No Known Activations