© 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. 39722
    Prev
    Next
    INDEX
    Explanations

    precise language

    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
     ਉ
    0.46
     ఆది
    0.46
     radioactive
    0.45
     radioactivity
    0.45
    4
    0.45
    ע
    0.44
    6
    0.44
     spectacle
    0.43
     peroxide
    0.42
     labyrinth
    0.42
    POSITIVE LOGITS
     entrevist
    0.55
    こちらの
    0.54
     ovog
    0.49
    この
    0.48
    沚
    0.48
     questa
    0.48
     tohoto
    0.47
     stycznia
    0.46
     această
    0.45
     இந்த
    0.45
    Activations Density 0.016%

    No Known Activations