© 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. 5531
    Prev
    Next
    INDEX
    Explanations

    endpoint enterprise assets

    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
     fucked
    0.96
     dianggap
    0.88
    unna
    0.84
    钉
    0.82
     rong
    0.78
     Theor
    0.77
     ligne
    0.76
    Nobody
    0.76
    辙
    0.75
     Cah
    0.74
    POSITIVE LOGITS
    Asset
    1.94
    asset
    1.74
     Asset
    1.70
     asset
    1.61
     assets
    1.58
     entertainment
    1.54
    entertainment
    1.53
    assets
    1.52
     Assets
    1.50
    Assets
    1.50
    Activations Density 0.242%

    No Known Activations