© 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
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2783
    Prev
    Next
    INDEX
    Explanations

    Okay,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     kinda
    0.87
     idk
    0.85
     dude
    0.83
     ahorita
    0.78
     wow
    0.78
     transitioning
    0.76
     cuz
    0.76
     =)
    0.75
     Verizon
    0.73
    Dude
    0.73
    POSITIVE LOGITS
    £
    1.23
     £
    1.13
    Cllr
    1.10
    NHS
    1.06
     NHS
    0.95
    Incidentally
    0.94
     Cllr
    0.91
    bbc
    0.91
     Bournemouth
    0.90
     Equally
    0.88
    Activations Density 0.262%

    No Known Activations