Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 1130
    Prev
    Next
    INDEX
    Explanations

    terms followed by a colon

    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_29_width_262k_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
     阅读全文
    2.37
     […]
    1.67
    )$\\
    1.64
     fi
    1.50
     例文帳に追加
    1.43
    $.\\
    1.33
    -\\
    1.29
    <eos>
    1.27
     Архивная
    1.27
     \\
    1.22
    POSITIVE LOGITS
    **
    3.19
    :**
    2.93
    .**
    2.90
    </strong>
    2.60
    **.
    2.55
    **:
    2.55
    **,
    2.52
    )**
    2.39
    **)
    2.33
    </b>
    2.17
    Activations Density 4.741%

    No Known Activations