© 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. 1910
    Prev
    Next
    INDEX
    Explanations

    its corners or Grendel

    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
     monog
    1.28
    ophages
    1.22
    antiated
    1.16
     laborales
    1.16
    omethane
    1.16
    okkh
    1.15
     trabalhadores
    1.14
    蚩
    1.13
    螌
    1.12
     JCV
    1.10
    POSITIVE LOGITS
    堂
    1.14
     lists
    1.06
     Lists
    1.04
     that
    0.99
    ↵↵↵
    0.99
     cuts
    0.98
    pr
    0.98
     such
    0.98
     top
    0.97
     preceding
    0.97
    Activations Density 0.169%

    No Known Activations