© 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. 166488
    Prev
    Next
    INDEX
    Explanations

    Affiliate

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

    automate, isolate, emulate

    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
    را
    0.47
     بابەت
    0.47
    服務
    0.46
     entendimento
    0.46
    TARIFF
    0.46
    Ꮅ
    0.46
    ادف
    0.45
    殄
    0.45
    番組
    0.45
    શા
    0.45
    POSITIVE LOGITS
    _
    0.55
    a
    0.55
    ular
    0.54
    input
    0.52
    in
    0.51
    ],
    0.51
    ].
    0.50
    agel
    0.50
    r
    0.50
    ])
    0.49
    Activations Density 0.000%

    No Known Activations