© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67108
    Prev
    Next
    INDEX
    Explanations

    describing past actions or states

    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
     necesitaba
    -1.48
     their
    -1.40
     that
    -1.37
     its
    -1.36
     all
    -1.32
     new
    -1.30
    になってしまう
    -1.27
    عارف
    -1.27
    を目指す
    -1.25
     when
    -1.22
    POSITIVE LOGITS
     was
    1.49
     Empfindung
    1.34
    <bos>
    1.26
     nación
    1.24
     Begleitung
    1.17
     Wahrnehmung
    1.15
    售价
    1.14
     astonishing
    1.13
    跑了
    1.12
     Erfüllung
    1.12
    Activations Density 0.069%

    No Known Activations