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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 966
    Prev
    Next
    INDEX
    Explanations

    states/actions applied

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     hehe
    1.50
     nice
    1.43
     nasty
    1.40
     shitty
    1.35
     ;)
    1.34
     cuz
    1.32
     shenanigans
    1.32
     haha
    1.23
     crappy
    1.21
     :)
    1.20
    POSITIVE LOGITS
     memiliki
    2.13
     inoltre
    2.10
     همچنین
    2.03
    采用
    1.97
     également
    1.96
     mengalami
    1.95
     regarded
    1.92
     dianggap
    1.92
     berbentuk
    1.90
     następnie
    1.89
    Activations Density 1.232%

    No Known Activations