© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4080
    Prev
    Next
    INDEX
    Explanations

    problems and 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
     discapac
    1.26
    赠
    1.22
     abat
    1.12
     playtime
    1.11
     penggunaan
    1.11
     altid
    1.10
    爱你
    1.07
     permiss
    1.07
    ífico
    1.06
     participa
    1.06
    POSITIVE LOGITS
    following
    2.00
    due
    1.92
    局面
    1.84
    torn
    1.77
     following
    1.77
    given
    1.71
    좌
    1.70
     Following
    1.69
     DUE
    1.67
    uidas
    1.67
    Activations Density 0.104%

    No Known Activations