© 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. 22-GEMMASCOPE-2-RES-262K
    4. 14232
    Prev
    Next
    INDEX
    Explanations

    boolean values and attributes

    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_22_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
     impeded
    1.33
    <?=
    1.31
    ❤️❤️
    1.30
    𝙜
    1.29
    ا
    1.18
    <%=
    1.16
     instilled
    1.15
     healed
    1.10
     eager
    1.09
     ژ
    1.08
    POSITIVE LOGITS
    ка
    1.29
    력
    1.21
    it
    1.18
    false
    1.17
    an
    1.14
    ان
    1.14
    true
    1.12
    myItemId
    1.09
    ۰
    1.08
    {%
    1.07
    Activations Density 0.001%

    No Known Activations