© 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. 14773
    Prev
    Next
    INDEX
    Explanations

    mode for numbers

    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
    诞生
    0.93
    <unused49>
    0.91
    örper
    0.91
     ایجاد
    0.88
    awać
    0.88
     değerlend
    0.87
     אשר
    0.86
    élément
    0.86
    妸
    0.85
    を用いた
    0.84
    POSITIVE LOGITS
     several
    2.10
     two
    1.86
     one
    1.69
     three
    1.66
     the
    1.63
     varios
    1.59
     multiple
    1.59
     a
    1.56
     flera
    1.54
     both
    1.53
    Activations Density 0.000%

    No Known Activations