© 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. 59633
    Prev
    Next
    INDEX
    Explanations

    examples showing output

    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
     of
    -2.02
    的气息
    -1.37
     who
    -1.31
     \
    -1.30
     unaweza
    -1.20
    6
    -1.18
     which
    -1.18
     parseFrom
    -1.16
    Nós
    -1.13
     kontakta
    -1.13
    POSITIVE LOGITS
    鲼
    1.49
     現貨
    1.45
     élimin
    1.40
    pherds
    1.38
     funzion
    1.35
    chinelo
    1.34
     contrase
    1.32
    erom
    1.31
    وردار
    1.31
    簓
    1.30
    Activations Density 0.095%

    No Known Activations