© 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-262K
    7. 93894
    Prev
    Next
    INDEX
    Explanations

    parentheses and colons

    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_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
     Hampton
    0.46
    s
    0.45
     Hue
    0.45
     Cohen
    0.44
    kin
    0.43
     rospy
    0.43
    h
    0.42
    c
    0.42
     Muse
    0.41
    holders
    0.41
    POSITIVE LOGITS
    𒀭
    0.51
    
    0.48
     ос
    0.46
    Says
    0.45
     ...]
    0.44
    ۞
    0.44
    enciones
    0.43
     introductions
    0.43
    భ
    0.43
     खूब
    0.42
    Activations Density 0.004%

    No Known Activations