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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34269
    Prev
    Next
    INDEX
    Explanations

    hallway table

    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
    ּוֹ
    -1.18
    ᾿
    -1.08
    Kons
    -1.06
    ִּ
    -1.05
     Θε
    -1.01
    ַּ
    -1.00
    ְּ
    -0.98
    ಝ
    -0.98
     бампер
    -0.97
     Inglaterra
    -0.96
    POSITIVE LOGITS
     and
    1.49
     somehow
    1.20
    하는
    1.01
    actually
    0.99
     things
    0.98
    Somehow
    0.98
    ﻩ
    0.96
    chanical
    0.95
     chré
    0.94
    LineColor
    0.93
    Activations Density 0.000%

    No Known Activations