© 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. 15049
    Prev
    Next
    INDEX
    Explanations

    outside activities or locations

    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
    ).
    -2.36
     and
    -2.13
     будет
    -2.11
    蓠
    -2.00
     traves
    -1.97
     peniten
    -1.97
    埽
    -1.95
    ﱠ
    -1.95
    😗
    -1.93
    踽
    -1.90
    POSITIVE LOGITS
    '
    2.88
    0
    2.63
    鲀
    2.28
    ᥬ
    2.22
    掼
    2.20
    ਗ਼
    2.11
    t
    2.06
     kurzen
    2.06
    下意识
    2.03
    8
    2.03
    Activations Density 0.014%

    No Known Activations