© 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. 874
    Prev
    Next
    INDEX
    Explanations

    human-computer interaction and acronyms

    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
     Chinatown
    0.71
     taiwan
    0.69
     verduras
    0.68
    蕃
    0.68
    台中
    0.66
     Guangdong
    0.66
    茶叶
    0.66
    ˙
    0.66
     Cantonese
    0.65
     vader
    0.65
    POSITIVE LOGITS
     IG
    1.98
     IB
    1.93
     IK
    1.92
     IA
    1.90
     ICS
    1.88
     ISC
    1.85
     IC
    1.83
     Ig
    1.83
     ICC
    1.75
     IO
    1.75
    Activations Density 0.801%

    No Known Activations