© 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. 40-GEMMASCOPE-2-RES-262K
    7. 167166
    Prev
    Next
    INDEX
    Explanations

    len(

    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_40_width_262k_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
    恻
    0.41
    Sizes
    0.41
     پس
    0.40
    Expected
    0.39
    Size
    0.38
    ണ്ണ
    0.37
     goles
    0.37
    Dimensions
    0.37
     dépassant
    0.37
     tamaños
    0.37
    POSITIVE LOGITS
    మె
    0.42
     Mei
    0.38
     ম্যা
    0.36
     메
    0.36
    ारण
    0.36
     мет
    0.36
     Ме
    0.35
     нико
    0.34
     May
    0.33
     maestro
    0.33
    Activations Density 0.007%

    No Known Activations