© 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. 123693
    Prev
    Next
    INDEX
    Explanations

    supernatural beliefs, intelligent AI, reset iPhone

    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
    ú
    0.44
    aturally
    0.43
    do
    0.43
    equality
    0.43
    addPreferredGap
    0.41
    最终
    0.41
    %,
    0.40
     `=`,
    0.40
     তৃ
    0.40
     ovoj
    0.40
    POSITIVE LOGITS
     یه
    0.42
    μένο
    0.41
     tính
    0.39
    фессиона
    0.39
    Transl
    0.39
    ographique
    0.38
     Communicate
    0.38
    竑
    0.38
     volcano
    0.38
    ка
    0.37
    Activations Density 0.016%

    No Known Activations