© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71855
    Prev
    Next
    INDEX
    Explanations

    undo and undue consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -2.45
    </tfoot>
    -2.34
    0
    -2.16
     einem
    -2.14
    of
    -2.11
     \
    -2.05
     czerwony
    -2.00
    ೣ
    -1.95
    嗑
    -1.92
     latter
    -1.91
    POSITIVE LOGITS
     墊
    2.47
    引言
    2.20
    ꦧ
    2.19
    퐸
    2.17
    …).
    2.17
     normais
    2.16
    旰
    2.11
    屣
    2.09
    緇
    2.09
    袮
    2.08
    Activations Density 0.004%

    No Known Activations