© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103412
    Prev
    Next
    INDEX
    Explanations

    strategies, causes, lawyer, cost, reviews

    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
     of
    -1.71
     with
    -1.57
     as
    -1.40
    清明
    -1.14
    )}=
    -1.10
     to
    -1.09
    )}=\
    -1.09
     and
    -1.07
    ἄ
    -1.01
     поэтому
    -1.00
    POSITIVE LOGITS
     abbin
    1.24
     étions
    1.20
    祈り
    1.16
     you
    1.16
    还想
    1.14
    给我们
    1.10
     komfor
    1.09
    能让
    1.09
    怎么能
    1.09
     funzion
    1.09
    Activations Density 0.250%

    No Known Activations