© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2750
    Prev
    Next
    INDEX
    Explanations

    respected experts and groups

    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
     Tiktok
    1.20
     🥰
    1.14
    🥰
    1.06
    🫶
    1.06
     whakap
    1.01
     dodgy
    1.01
     inbuilt
    1.00
     Whatsapp
    0.99
     touristic
    0.98
    🥳
    0.97
    POSITIVE LOGITS
     ERISA
    1.20
     foodservice
    1.13
     multifamily
    1.11
     FDIC
    1.06
     HIPAA
    0.96
    ꯠ
    0.96
     Hispanic
    0.95
     industry
    0.94
     webcast
    0.93
     ANSI
    0.93
    Activations Density 1.589%

    No Known Activations