© 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. 5456
    Prev
    Next
    INDEX
    Explanations

    the better

    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
     Prakash
    1.26
    ể
    1.26
     жүкт
    1.22
    を得
    1.21
     istem
    1.21
     Reprint
    1.18
    acea
    1.14
    )+"]
    1.13
    ervlak
    1.12
    avirus
    1.10
    POSITIVE LOGITS
     heads
    1.43
    й
    1.35
    قات
    1.35
     head
    1.33
     зага
    1.29
    heads
    1.28
     shared
    1.28
    бята
    1.24
     facts
    1.24
    里的
    1.23
    Activations Density 0.034%

    No Known Activations