© 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. 8703
    Prev
    Next
    INDEX
    Explanations

    answer, usage

    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
    ISING
    0.46
    HA
    0.41
     exercices
    0.40
    Trimethyl
    0.39
    ⓗ
    0.39
     mimetype
    0.39
    details
    0.38
     baud
    0.38
     bolognese
    0.38
    ranges
    0.38
    POSITIVE LOGITS
    走进
    0.48
    ș
    0.48
     મને
    0.44
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.44
     roaring
    0.44
     Showcase
    0.43
    ama
    0.43
    personen
    0.43
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.42
     számára
    0.42
    Activations Density 0.053%

    No Known Activations