© 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. 31-GEMMASCOPE-2-RES-262K
    7. 19330
    Prev
    Next
    INDEX
    Explanations

    line by line code

    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
    の開発
    0.39
     limitar
    0.38
     چال
    0.38
     temporada
    0.37
    "":
    0.36
     regreso
    0.36
    วัฒ
    0.36
     gostaria
    0.35
     cocok
    0.35
     valt
    0.35
    POSITIVE LOGITS
    его
    0.46
     nutritive
    0.42
    dataGridView
    0.42
     dandruff
    0.41
     fructose
    0.40
     herbicides
    0.40
     horseradish
    0.38
    嘌
    0.38
     cannabinoids
    0.38
    。「
    0.38
    Activations Density 0.007%

    No Known Activations