© 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. 178294
    Prev
    Next
    INDEX
    Explanations

    supporting claims and origins

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

    serial port

    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
     мне
    0.49
    }}<
    0.48
     könne
    0.45
    !
    0.45
    )。
    0.44
    cos
    0.43
    屏
    0.42
    říklad
    0.41
    見
    0.41
     Waste
    0.41
    POSITIVE LOGITS
     სახელმწიფ
    0.47
     завода
    0.46
     nationwide
    0.46
     authoritative
    0.45
    ieli
    0.45
    一把
    0.45
     patria
    0.45
     اسرائیل
    0.45
     superseded
    0.45
    ı
    0.44
    Activations Density 0.000%

    No Known Activations