© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108125
    Prev
    Next
    INDEX
    Explanations

    intrinsically disordered peptide

    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
     свого
    0.46
     RxSwift
    0.45
     Ihrem
    0.44
     ఇప్పటికే
    0.44
    峣
    0.44
     Swimming
    0.43
    posals
    0.43
     Terraform
    0.43
     LiDAR
    0.43
    设定
    0.42
    POSITIVE LOGITS
    स
    0.54
    '
    0.49
    ed
    0.49
    ەکە
    0.49
    ケ
    0.48
    ക
    0.47
    ce
    0.47
    Lyon
    0.47
    רו
    0.47
    gray
    0.47
    Activations Density 0.012%

    No Known Activations