© 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. 129911
    Prev
    Next
    INDEX
    Explanations

    in locations and contexts

    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
    “
    -1.40
     SITY
    -1.38
    ahhh
    -1.37
    </h2>
    -1.35
    B
    -1.34
    ኋ
    -1.34
     ]}
    -1.34
     which
    -1.30
    cive
    -1.28
     divisa
    -1.28
    POSITIVE LOGITS
    issipp
    1.48
     Inſ
    1.33
     naughty
    1.33
     tapasztal
    1.30
     berakhir
    1.28
     помощью
    1.27
     undoing
    1.27
     Houſe
    1.27
     вона
    1.25
     '-';
    1.24
    Activations Density 0.122%

    No Known Activations