© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41136
    Prev
    Next
    INDEX
    Explanations

    detecting abnormal conditions

    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
    </h3>
    -3.02
    “,
    -2.38
    actéristi
    -2.31
    部分を
    -2.28
    徇
    -2.28
    艫
    -2.17
    썽
    -2.16
            
    -2.14
     /\.(
    -2.13
    síða
    -2.13
    POSITIVE LOGITS
    s
    3.03
     was
    2.88
    ꠥ
    2.59
    ی
    2.02
    巨大的
    1.95
    >
    1.93
    垕
    1.91
    </b>
    1.91
     deceiving
    1.89
     löst
    1.82
    Activations Density 0.000%

    No Known Activations