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. 6800
    Prev
    Next
    INDEX
    Explanations

    low population, closed door, classic logic

    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
    .
    0.76
    ,
    0.68
      
    0.68
    ↵↵
    0.66
     the
    0.63
     
    0.63
     -
    0.63
     a
    0.61
    ...
    0.60
    ↵
    0.58
    POSITIVE LOGITS
    zynarod
    0.77
    goài
    0.77
    𒅀
    0.73
    쮿
    0.72
    mataspid
    0.71
    Radiux
    0.71
    <unused600>
    0.71
     kttt
    0.71
    𒉣
    0.71
    <unused996>
    0.71
    Activations Density 11.149%

    No Known Activations