© 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. 15328
    Prev
    Next
    INDEX
    Explanations

    reaching a state or limit

    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
    u
    -2.86
    𓐍
    -2.23
    arraycopy
    -2.08
     htmlFor
    -2.02
    quía
    -2.00
     سمع
    -1.98
    蘗
    -1.96
    巔
    -1.95
    "}}>
    -1.95
    the
    -1.95
    POSITIVE LOGITS
    愎
    2.72
    "
    2.58
     They
    2.48
    .
    2.36
    さんから
    2.19
    鈊
    2.14
    ࿚
    2.09
     reached
    2.08
    乆
    2.08
     Each
    2.05
    Activations Density 0.013%

    No Known Activations