© 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-65K
    7. 17027
    Prev
    Next
    INDEX
    Explanations

    intervention, control, or examples

    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_65k_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
     มาก
    0.54
    ঃ
    0.47
     คุณ
    0.45
    รู้จัก
    0.44
    ４
    0.43
    ซื้อ
    0.41
     Pickup
    0.40
    ถม
    0.39
    ೧
    0.39
    Jogo
    0.38
    POSITIVE LOGITS
     हस्तक्षेप
    0.43
    mittent
    0.42
     intervention
    0.42
    abhavena
    0.42
     सास
    0.41
     নিয়ন্ত্রণে
    0.40
    vodu
    0.40
     interventions
    0.40
    izoph
    0.40
    softmax
    0.39
    Activations Density 0.001%

    No Known Activations