© 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. 32610
    Prev
    Next
    INDEX
    Explanations

    means that

    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
    _
    0.46
    Row
    0.42
     stressors
    0.42
    ishments
    0.40
    intentional
    0.40
    \\
    0.40
    pm
    0.40
     breaths
    0.40
    }{
    0.40
    Weapon
    0.39
    POSITIVE LOGITS
     McKin
    0.45
    ರಿಗೆ
    0.45
    женер
    0.43
    getMetering
    0.43
     Entered
    0.43
    عدد
    0.42
    URUK
    0.42
    禊
    0.41
    ্রিক
    0.41
    ការព
    0.41
    Activations Density 0.000%

    No Known Activations