© 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. 5334
    Prev
    Next
    INDEX
    Explanations

    ensuring compliance and integrity

    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
    folios
    1.67
    yang
    1.62
    s
    1.50
    咬
    1.49
    e
    1.48
    anding
    1.47
    uur
    1.47
    lede
    1.46
    }}{\
    1.45
    tir
    1.45
    POSITIVE LOGITS
     обязан
    1.02
    macher
    0.96
     mắc
    0.96
     funcionario
    0.95
     fertilization
    0.94
    ᅠ
    0.93
    ázej
    0.93
    aventure
    0.92
    чением
    0.92
    ERSHIP
    0.92
    Activations Density 0.156%

    No Known Activations