© 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. 22-GEMMASCOPE-RES-131K
    7. 16006
    Prev
    Next
    INDEX
    Explanations

    status or state indicators

    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_22/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
     vermutlich
    -0.98
     Однако
    -0.98
    就算
    -0.95
     colossal
    -0.91
    𝔱
    -0.91
    sities
    -0.91
    su
    -0.91
     Профиль
    -0.91
     disorganized
    -0.90
    ᴠ
    -0.90
    POSITIVE LOGITS
     status
    1.66
     on
    1.45
    状态
    1.27
     statuses
    1.19
     trạng
    1.16
     getStatus
    1.16
    的状态
    1.16
    狀態
    1.15
    status
    1.14
     state
    1.11
    Activations Density 0.022%

    No Known Activations