© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3506
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relations or conditions

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

    phrasal connectors

    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_53_width_65k_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
    ´
    0.40
     It
    0.35
    ↵
    0.34
     ¨
    0.34
     Så
    0.33
     We
    0.33
    ised
    0.33
     \
    0.32
     Appart
    0.32
     &
    0.32
    POSITIVE LOGITS
     زیادہ
    0.37
     pesky
    0.36
    <unused52>
    0.35
     осигурање
    0.35
     அவற்றை
    0.35
     జరిగ
    0.35
     অধিক
    0.34
     aerosols
    0.34
    <unused1782>
    0.33
     PDFs
    0.33
    Activations Density 0.157%

    No Known Activations