© 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. 128865
    Prev
    Next
    INDEX
    Explanations

    initials followed by periods or names

    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
    3
    -2.42
    2
    -2.19
    ”
    -2.17
    焄
    -2.16
    </b>
    -2.14
     vorhandenen
    -2.13
    最も
    -2.06
    with
    -2.03
    個人的に
    -2.03
    5
    -1.96
    POSITIVE LOGITS
    ❄
    1.95
    🌻
    1.88
     and
    1.88
    😹
    1.80
    🥱
    1.78
    😗
    1.69
    RFID
    1.69
    😰
    1.68
    🎅
    1.65
    😲
    1.64
    Activations Density 0.011%

    No Known Activations