© 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. 310
    Prev
    Next
    INDEX
    Explanations

    future prediction or condition

    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
    なー
    -1.27
     recibido
    -1.27
     anadolu
    -1.23
    ことはない
    -1.20
     anuncia
    -1.16
     kimdir
    -1.14
     отвечает
    -1.13
     lately
    -1.13
     lasted
    -1.10
    なあ
    -1.10
    POSITIVE LOGITS
    𖤍
    1.22
     vermutlich
    1.19
     will
    1.14
     Maybe
    1.11
     likely
    1.08
    ourites
    1.04
     Probably
    1.03
    螓
    1.02
     Unless
    1.02
    Blockly
    1.01
    Activations Density 0.086%

    No Known Activations