© 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. 40-GEMMASCOPE-2-RES-262K
    4. 224505
    Prev
    Next
    INDEX
    Explanations

    specific word pairings and definitions

    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_40_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
     verde
    0.40
     Verde
    0.39
    ol
    0.38
     aforementioned
    0.38
    oso
    0.38
    ubb
    0.37
    ood
    0.36
    뿐
    0.36
    ഊ
    0.36
    しくは
    0.36
    POSITIVE LOGITS
    зить
    0.39
    ນິກ
    0.39
     সঠিক
    0.38
    ንዳንድ
    0.38
    াফিক
    0.38
     backpacks
    0.38
    公式サイト
    0.38
    чатки
    0.38
     நிமிடங்கள்
    0.37
     ambulances
    0.37
    Activations Density 0.000%

    No Known Activations