© 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. 5154
    Prev
    Next
    INDEX
    Explanations

    movement direction

    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
     ගැනීම
    0.46
    üğünüz
    0.43
     ಹಿಂದ
    0.43
    ivalent
    0.43
    摒
    0.42
     пыта
    0.41
     //=>
    0.41
    üdis
    0.40
    cevam
    0.40
    ừa
    0.39
    POSITIVE LOGITS
     multiplied
    0.45
     controller
    0.36
    0.36
     flying
    0.36
     nails
    0.35
     our
    0.35
     maintaining
    0.35
     Controller
    0.35
    而出
    0.35
     principals
    0.34
    Activations Density 0.076%

    No Known Activations