© 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
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 559
    Prev
    Next
    INDEX
    Explanations

    code formatting in explanations

    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
    odim
    0.79
    )=-
    0.77
    )+(
    0.77
    /]
    0.75
    )=(
    0.74
    żli
    0.74
    ]=(
    0.74
    xim
    0.73
    ])+
    0.72
    ]=-
    0.72
    POSITIVE LOGITS
     Laurence
    1.48
     Villan
    1.46
     Versailles
    1.41
    ERA
    1.37
     bast
    1.36
     Shaf
    1.36
     Código
    1.35
     modific
    1.34
     Afin
    1.34
     Susana
    1.34
    Activations Density 0.047%

    No Known Activations