© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63551
    Prev
    Next
    INDEX
    Explanations

    Learning paths and variations

    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
     Pudding
    0.49
    _
    0.47
     Pythagoras
    0.47
     Babylon
    0.46
     explains
    0.46
     уг
    0.45
     worsens
    0.45
     அரி
    0.44
     misused
    0.44
     ตำ
    0.44
    POSITIVE LOGITS
    applicazione
    0.46
    षा
    0.45
     διαφορε
    0.45
    幄
    0.45
    ዋል።
    0.44
    supplied
    0.44
    𝗮
    0.44
    ulata
    0.44
    equilib
    0.43
    मन्त्री
    0.43
    Activations Density 0.007%

    No Known Activations