© 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. 221431
    Prev
    Next
    INDEX
    Explanations

    verified unbiased reviews

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

    escalating tensions or planned rollout

    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
    ل
    0.55
    ه
    0.54
    ה
    0.54
    हीर
    0.51
    ጒ
    0.50
     bals
    0.50
    ⴼ
    0.50
     penyimpanan
    0.50
     oynuyoruz
    0.49
    ഹി
    0.49
    POSITIVE LOGITS
    ance
    0.52
    <sub>
    0.51
    ONI
    0.49
    aurus
    0.47
    idy
    0.47
    ily
    0.47
    CHT
    0.46
    oka
    0.46
    |
    0.46
    ary
    0.45
    Activations Density 0.000%

    No Known Activations