© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 53600
    Prev
    Next
    INDEX
    Explanations

    qualifying or contrasting statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Zoo
    0.46
    솎
    0.43
     genutzt
    0.42
    Ûn
    0.42
     affirme
    0.42
    берриз
    0.42
    ्वल
    0.41
    Meine
    0.40
     yaparak
    0.40
     wisata
    0.40
    POSITIVE LOGITS
     .
    0.42
    ATIV
    0.42
     external
    0.41
     ノ
    0.40
    ோ
    0.39
     communicator
    0.39
     context
    0.39
     protrusions
    0.39
     спа
    0.38
     уг
    0.38
    Activations Density 0.006%

    No Known Activations