© 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. 87056
    Prev
    Next
    INDEX
    Explanations

    agents, Lucas, must, force, Hence, is

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

    moving beyond

    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
    habitants
    0.49
    Tambah
    0.46
    <unused25>
    0.44
    ログイン
    0.44
     ಹ
    0.43
    精致
    0.43
    export
    0.42
     見
    0.41
    ambah
    0.41
    ｴ
    0.40
    POSITIVE LOGITS
     étaient
    0.52
     Reserves
    0.52
     comme
    0.49
     wcześ
    0.49
    𝐓
    0.49
     drugi
    0.47
     поперед
    0.46
     secondo
    0.46
     предыду
    0.46
     genauso
    0.46
    Activations Density 0.001%

    No Known Activations