© 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. 29498
    Prev
    Next
    INDEX
    Explanations

    GPT-3.5 Turbo, stat block, spot instances

    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
     DROP
    0.58
     उन्हें
    0.46
    녠
    0.46
    彼此
    0.43
    癸
    0.42
    探
    0.41
    কে
    0.41
     buzzing
    0.41
    明天
    0.41
    註
    0.41
    POSITIVE LOGITS
    illère
    0.43
    geschwindigkeit
    0.41
     |-
    0.40
    сист
    0.40
     obeys
    0.39
     በተጨማሪ
    0.38
    лся
    0.38
    шается
    0.38
     cane
    0.38
    |)
    0.38
    Activations Density 0.001%

    No Known Activations