© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199819
    Prev
    Next
    INDEX
    Explanations

    Common Sense Reasoning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    ة
    0.49
    <0x82>
    0.48
    Tam
    0.48
    <0xBF>
    0.46
    人們
    0.46
    ائح
    0.46
    璜
    0.46
    邃
    0.45
    ेश
    0.44
    Celestial
    0.43
    POSITIVE LOGITS
     dirt
    0.45
     moderated
    0.44
    ついて
    0.41
    ضای
    0.41
    dol
    0.41
     オ
    0.40
     ghetto
    0.40
    0.40
     juicy
    0.40
     Drupal
    0.40
    Activations Density 0.007%

    No Known Activations