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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11360
    Prev
    Next
    INDEX
    Explanations

    because of connection

    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
     reveló
    -1.02
     Préférences
    -1.02
    但她
    -0.99
    Nella
    -0.96
     teilen
    -0.94
     erweit
    -0.93
     integriert
    -0.93
     afbeelding
    -0.92
     pesar
    -0.91
     inició
    -0.90
    POSITIVE LOGITS
     him
    2.14
     their
    1.57
     his
    1.45
     onun
    1.33
     this
    1.24
     hänen
    1.22
     these
    1.15
     your
    1.13
     them
    1.08
     he
    1.03
    Activations Density 0.036%

    No Known Activations