© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159949
    Prev
    Next
    INDEX
    Explanations

    procedures, handbags, checks, joining, himself, We buy, your home, issues

    np_acts-logits-general · gemini-2.5-flash-lite

    self-awareness and limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     realizan
    0.46
    čí
    0.46
    <0x86>
    0.43
    <0x96>
    0.43
     deliver
    0.41
     supplying
    0.41
    тя
    0.41
    čia
    0.41
     đua
    0.41
     rescues
    0.41
    POSITIVE LOGITS
     التى
    0.54
     أقل
    0.49
     थो
    0.48
     المعروف
    0.48
     бело
    0.48
     टुडे
    0.46
     Lern
    0.46
     ненави
    0.46
    頩
    0.46
     thymus
    0.46
    Activations Density 0.000%

    No Known Activations