© 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. 84821
    Prev
    Next
    INDEX
    Explanations

    'K' followed by punctuation or variable name

    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
     nî
    -1.30
     anggaran
    -1.17
    𝑔
    -1.16
     essentially
    -1.13
    𝑆
    -1.13
    Relation
    -1.12
     adequate
    -1.11
     almost
    -1.10
     most
    -1.09
     långt
    -1.09
    POSITIVE LOGITS
    lamations
    1.30
    InstrumentedTest
    1.25
     parfois
    1.20
     иногда
    1.19
    selbe
    1.18
     駅前
    1.17
     Après
    1.16
    Дина
    1.14
     garg
    1.14
    Ahora
    1.14
    Activations Density 0.067%

    No Known Activations