© 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. 108845
    Prev
    Next
    INDEX
    Explanations

    Benedict Arnold and cord

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

    arbitration against

    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
    Negative Logits
     VIP
    0.49
    Advertisement
    0.48
    رام
    0.47
     velocità
    0.47
    "./
    0.45
    Credit
    0.45
     fundamentales
    0.45
     Promotional
    0.45
     समर्थक
    0.44
    "
    0.44
    POSITIVE LOGITS
    дьми
    0.49
    дка
    0.49
     thường
    0.47
    to
    0.46
     frmt
    0.46
     अक्सर
    0.44
    anamh
    0.44
     always
    0.44
     обычно
    0.43
     簡単
    0.41
    Activations Density 0.000%

    No Known Activations