© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71485
    Prev
    Next
    INDEX
    Explanations

    database schema and connection details

    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
     in
    -1.49
     and
    -1.46
     during
    -1.35
     these
    -1.28
     undeniably
    -1.26
     one
    -1.20
     spurred
    -1.18
     only
    -1.16
    žku
    -1.16
     at
    -1.14
    POSITIVE LOGITS
     hundert
    1.25
    [],
    1.22
     การ
    1.19
     erzeugt
    1.19
     musst
    1.18
     restricciones
    1.17
    放弃
    1.16
     ggf
    1.15
     ม
    1.14
     geleg
    1.13
    Activations Density 0.005%

    No Known Activations