© 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. 17-GEMMASCOPE-2-RES-16K
    4. 3282
    Prev
    Next
    INDEX
    Explanations

    testing, key, secure, threaded

    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
    deh
    1.09
     incógn
    1.07
    Undo
    1.07
     ajud
    1.03
     veste
    1.03
    ه
    1.03
     mundial
    1.01
     independente
    1.00
     eixo
    1.00
    quele
    1.00
    POSITIVE LOGITS
    isinde
    1.14
     fis
    1.12
    ترض
    1.10
     $\%$
    1.07
    polygon
    1.06
    াস্ট
    1.05
    ুজ
    1.04
    ))>
    1.02
    ْت
    1.02
     বলিয়
    1.01
    Activations Density 0.027%

    No Known Activations