© 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. 9136
    Prev
    Next
    INDEX
    Explanations

    yes or no answers

    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
    ный
    1.05
     dull
    1.01
    ি
    1.00
    状况
    0.99
    vođa
    0.96
     strept
    0.93
    Y
    0.93
    T
    0.92
     Sw
    0.92
     boring
    0.92
    POSITIVE LOGITS
    트워크
    1.37
    ení
    1.31
     eens
    1.29
    hiva
    1.28
    .%
    1.26
     encapsulation
    1.23
     particulières
    1.22
    ငံ
    1.21
     obligaciones
    1.20
     формування
    1.19
    Activations Density 0.114%

    No Known Activations