© 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. 35752
    Prev
    Next
    INDEX
    Explanations

    Albany County

    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
    一会儿
    -1.21
     Before
    -1.09
     However
    -1.05
     their
    -1.03
    おわりに
    -0.96
    に見える
    -0.95
    satunya
    -0.93
    わけです
    -0.93
    つづく
    -0.93
     veckan
    -0.93
    POSITIVE LOGITS
    や
    1.46
     décider
    1.20
     muchacha
    1.19
     unga
    1.18
    셸
    1.17
    などを
    1.16
     perſon
    1.14
     abito
    1.14
     ۱۳۹
    1.13
     hasn
    1.13
    Activations Density 0.000%

    No Known Activations