© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112181
    Prev
    Next
    INDEX
    Explanations

    common connectors with subsequent words

    np_acts-logits-general · gemini-2.5-flash-lite

    service that handles tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     किर
    0.46
    Έ
    0.43
    🌾
    0.43
     기다
    0.42
     Ξ
    0.42
    ื
    0.42
    睬
    0.42
     Έ
    0.42
    运气
    0.42
    北海道
    0.41
    POSITIVE LOGITS
    aware
    0.47
     innehåller
    0.46
     ضرور
    0.45
     Aware
    0.45
    нтэр
    0.44
     với
    0.44
    rutt
    0.43
     جامع
    0.43
     gồm
    0.43
    contain
    0.41
    Activations Density 0.002%

    No Known Activations