© 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. 4387
    Prev
    Next
    INDEX
    Explanations

    final decisions after discussion

    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
     departments
    1.35
    هن
    1.32
    她们
    1.31
     celles
    1.27
     endometrial
    1.25
     absences
    1.23
    zczeg
    1.22
    쁠
    1.22
     themselves
    1.19
    هَا
    1.19
    POSITIVE LOGITS
     Taro
    1.08
     McInt
    1.03
    ucu
    1.02
     Lugo
    1.00
     yc
    1.00
    aton
    0.99
    asting
    0.98
    ástico
    0.98
    сто
    0.95
    rew
    0.93
    Activations Density 0.037%

    No Known Activations