© 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. 10-GEMMASCOPE-RES-131K
    7. 124131
    Prev
    Next
    INDEX
    Explanations

    conference sessions and talks

    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
     Surprisingly
    -1.30
     Ironically
    -1.27
     other
    -1.27
    Surprisingly
    -1.26
     notwendigen
    -1.23
     Sometimes
    -1.21
     qualquer
    -1.20
     Despite
    -1.20
     bekym
    -1.19
     entsprechenden
    -1.17
    POSITIVE LOGITS
     "
    1.30
    ße
    1.28
     faudra
    1.20
     seperate
    1.20
     baden
    1.18
     soient
    1.17
    mutations
    1.13
     there
    1.13
     part
    1.11
    iczny
    1.11
    Activations Density 0.044%

    No Known Activations