© 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-IT
    3. 9-GEMMASCOPE-2-RES-16K
    4. 49
    Prev
    Next
    INDEX
    Explanations

    access to, close friend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ενός
    2.03
     footing
    2.03
    𝐚
    2.02
    d
    1.93
    いますが
    1.92
     μπορού
    1.91
    𝐨
    1.90
    ор
    1.88
     já
    1.88
    cpy
    1.87
    POSITIVE LOGITS
    Iddict
    3.04
     sores
    2.45
     spaced
    2.40
     तौर
    2.23
    आम
    2.12
    spotify
    2.10
     Purchase
    2.07
    жек
    2.07
    OrCreate
    2.06
    ၚ
    2.06
    Activations Density 5.244%

    No Known Activations