© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1937
    Prev
    Next
    INDEX
    Explanations

    filling a void

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     সাথেই
    0.62
     C
    0.59
     perut
    0.58
    ই
    0.58
     describes
    0.55
    legel
    0.55
     se
    0.54
     SE
    0.53
     describe
    0.52
     movies
    0.52
    POSITIVE LOGITS
     더욱
    1.02
     மேலும்
    1.01
     ולה
    1.01
    并
    1.00
     وتح
    1.00
    从而
    0.99
     وت
    0.97
     thereby
    0.96
     وتن
    0.92
     ลด
    0.92
    Activations Density 2.284%

    No Known Activations