© 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. 13256
    Prev
    Next
    INDEX
    Explanations

    starts of phrases or questions

    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
     türkiye
    -1.11
     Preferencias
    -1.07
    וּ
    -1.07
    зировать
    -1.05
     Iš
    -1.04
     hébergement
    -1.03
     verhind
    -1.02
     herbe
    -1.01
    ָד
    -1.01
    POSITIVE LOGITS
    曲は
    1.07
    ׇ
    1.01
     ,
    0.98
     although
    0.94
     and
    0.93
     Ihm
    0.93
     our
    0.90
     all
    0.90
     While
    0.90
     attire
    0.90
    Activations Density 0.000%

    No Known Activations