© 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-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 661
    Prev
    Next
    INDEX
    Explanations

    understanding text and context

    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_17_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
    ма
    1.51
    on
    1.40
    ટ
    1.23
    ter
    1.23
    ت
    1.18
    ะ
    1.08
    ো
    1.06
    擊
    1.05
    ்
    1.05
    लैंड
    1.04
    POSITIVE LOGITS
     biết
    1.60
    ably
    1.43
     dawned
    1.42
     firsthand
    1.36
     Grundlagen
    1.25
     Beside
    1.20
     hindsight
    1.20
    BeginInit
    1.19
     comprenant
    1.19
    떤
    1.18
    Activations Density 0.414%

    No Known Activations