© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 71500
    Prev
    Next
    INDEX
    Explanations

    copy and paste tasks

    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
     юби
    0.46
    ItemsSource
    0.45
    uncie
    0.45
     obtaining
    0.44
     upgraded
    0.44
     licences
    0.43
    Incrementor
    0.42
    ⿸
    0.42
    их
    0.42
     入っ
    0.42
    POSITIVE LOGITS
     রোগী
    0.44
     pacient
    0.42
     krit
    0.42
    جن
    0.41
    呼吸
    0.41
    患者
    0.40
    喘
    0.40
    了他
    0.39
    ี
    0.39
    艺术
    0.39
    Activations Density 0.005%

    No Known Activations