© 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. 128489
    Prev
    Next
    INDEX
    Explanations

    obliterate, oblique, obscure, obstructed

    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
    ar
    -3.36
    )
    -2.72
    ſu
    -2.41
     vand
    -2.27
    ㍑
    -2.16
    ſſen
    -2.14
    之事
    -2.14
    没有了
    -2.13
    る
    -2.09
    嫑
    -2.09
    POSITIVE LOGITS
    ↵
    3.36
    งิน
    2.20
     Vielzahl
    2.06
    枓
    2.03
    ).
    2.03
     articulate
    2.02
    çok
    1.97
     unnecessarily
    1.96
     necesaria
    1.93
     cheerfully
    1.92
    Activations Density 0.010%

    No Known Activations