© 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
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3018
    Prev
    Next
    INDEX
    Explanations

    future, hope, and sustainability

    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
     overfitting
    1.09
    featur
    1.08
     qualités
    1.05
     Complexes
    1.03
    豢
    0.99
     Vorg
    0.98
     mắc
    0.98
     hMut
    0.97
    酩
    0.97
     Downloading
    0.97
    POSITIVE LOGITS
     tomorrow
    1.63
     brighter
    1.57
    轍
    1.47
     tule
    1.41
     solution
    1.40
    solution
    1.39
     united
    1.35
    ukunft
    1.35
    結束
    1.35
    tomorrow
    1.35
    Activations Density 0.149%

    No Known Activations