© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119457
    Prev
    Next
    INDEX
    Explanations

    imprisonment, imprisonment, imprisoned, jailed

    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
    汌
    -2.81
    在
    -2.22
     importantly
    -2.20
    𖣘
    -2.16
    D
    -2.16
     atrav
    -2.14
    蟶
    -2.14
    —
    -2.11
     图
    -2.05
    НОГО
    -2.05
    POSITIVE LOGITS
    ization
    2.78
    ).
    2.52
    霂
    2.31
    d
    2.28
    ção
    2.27
    賅
    2.27
     generando
    2.23
    目的是
    2.22
    汭
    2.14
    f
    2.13
    Activations Density 0.002%

    No Known Activations