© 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. 34031
    Prev
    Next
    INDEX
    Explanations

    numbers following titles

    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
    ↵
    -2.11
     parfüm
    -1.58
     circunstancia
    -1.52
     parfü
    -1.47
    หรือ
    -1.34
    憷
    -1.30
     kabát
    -1.30
     kompati
    -1.30
    ⛤
    -1.30
     mikrofon
    -1.29
    POSITIVE LOGITS
     Before
    1.64
    J
    1.49
    j
    1.43
    V
    1.41
     With
    1.41
     When
    1.40
     There
    1.39
     at
    1.38
    Just
    1.35
    C
    1.35
    Activations Density 0.014%

    No Known Activations