© 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. 143393
    Prev
    Next
    INDEX
    Explanations

    calculations and differences

    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
    VCTarget
    0.47
    arzt
    0.46
    ༣
    0.45
    समा
    0.43
    Prospect
    0.43
    ack
    0.43
     trzec
    0.43
     mécanique
    0.42
    ร
    0.42
    ye
    0.41
    POSITIVE LOGITS
     propio
    0.45
    丰富的
    0.44
    lang
    0.44
     attempted
    0.41
     putative
    0.40
     inhibited
    0.39
     connot
    0.39
     lagged
    0.39
     precluded
    0.38
     sobri
    0.38
    Activations Density 0.012%

    No Known Activations