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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 21920
    Prev
    Next
    INDEX
    Explanations

    irrespective of

    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
    |$.
    -2.48
    </b>
    -2.42
     With
    -2.31
    ))->
    -2.31
    "}}>
    -2.30
    >):
    -2.27
    </i>
    -2.27
    iconductors
    -2.17
    יה
    -2.16
     to
    -2.14
    POSITIVE LOGITS
    ୌ
    2.58
     ſta
    2.56
    ꦸ
    2.55
    鹟
    2.55
     iſt
    2.52
    0
    2.36
    灩
    2.34
    bezpiecz
    2.30
    ...\
    2.23
     dezelve
    2.23
    Activations Density 0.001%

    No Known Activations