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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 14600
    Prev
    Next
    INDEX
    Explanations

    itself or themselves

    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
    િન
    0.72
    мпаваць
    0.66
     aras
    0.65
    ूर
    0.63
    摯
    0.63
    ствую
    0.62
     場合
    0.61
    }^{*}$
    0.60
     PCE
    0.59
    取締
    0.59
    POSITIVE LOGITS
     itself
    2.40
    本身
    2.14
     themselves
    2.06
     alone
    2.03
    本身的
    1.88
     자체
    1.87
     sendiri
    1.78
    单独
    1.73
     자체가
    1.70
     Alone
    1.70
    Activations Density 0.079%

    No Known Activations