© 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. 1406
    Prev
    Next
    INDEX
    Explanations

    concluding phrases

    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
     and
    2.57
     và
    2.55
    和社会
    2.44
    ?:
    2.33
    และ
    2.16
    !:
    2.16
    and
    2.03
    和
    2.01
    和服务
    1.98
    ’:
    1.95
    POSITIVE LOGITS
     consequently
    4.29
     sebagainya
    4.11
     hence
    4.09
     whatnot
    4.03
     thereby
    3.91
     therefore
    3.81
     thus
    3.80
     somit
    3.66
     subsequently
    3.56
     consequent
    3.54
    Activations Density 3.589%

    No Known Activations