© 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. 22-GEMMASCOPE-2-RES-262K
    7. 14147
    Prev
    Next
    INDEX
    Explanations

    end of sentence or question

    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
    有两种
    0.88
    <eos>
    0.81
    :
    0.65
     যথা
    0.63
    ziehungs
    0.63
     ሁለት
    0.62
     যেমন
    0.62
    :");
    0.61
    :";
    0.61
    ./
    0.61
    POSITIVE LOGITS
     These
    1.88
    These
    1.86
    etc
    1.82
     etc
    1.77
     these
    1.74
     Etc
    1.69
    these
    1.67
     ইত্যাদি
    1.67
    这些
    1.65
     all
    1.65
    Activations Density 0.281%

    No Known Activations