© 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. 85156
    Prev
    Next
    INDEX
    Explanations

    contact and communication

    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
     epidemic
    -1.20
     magnify
    -1.17
     Out
    -1.15
     extensive
    -1.14
     User
    -1.13
    nt
    -1.13
     explosion
    -1.08
    banyak
    -1.08
    ınız
    -1.08
     उन्होंने
    -1.06
    POSITIVE LOGITS
    簠
    1.30
     viejas
    1.18
     if
    1.16
    httpMethod
    1.14
    回目の
    1.13
     boya
    1.10
     culturale
    1.10
    ativamente
    1.09
    ഥ
    1.08
     regione
    1.07
    Activations Density 0.156%

    No Known Activations